© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33033
    Prev
    Next
    INDEX
    Explanations

    Beck depression

    np_acts-logits-general · gemini-2.5-flash-lite

    items in structured data or code, particularly in numbered lists, tables, or programming syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates strongly on tokens containing numerals or numeric sequences (e.g. digits, numeric codes, or measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     will
    -1.27
     that
    -1.23
    imbangan
    -0.90
     can
    -0.80
     by
    -0.78
    鴉
    -0.77
     semuanya
    -0.77
     Vielfalt
    -0.77
     putting
    -0.75
     kés
    -0.75
    POSITIVE LOGITS
    iked
    0.91
    lijkse
    0.91
    launched
    0.89
    CONTINUE
    0.84
    沐浴
    0.84
    agreed
    0.83
     tabela
    0.82
    zelf
    0.81
     articol
    0.80
     morts
    0.80
    Activations Density 0.050%

    No Known Activations