© 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. 33798
    Prev
    Next
    INDEX
    Explanations

    separators and punctuation

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

    The neuron activates on numeric literals (especially decimal or floating‐point numbers).

    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
     feltro
    -1.12
     dentista
    -1.10
    Porte
    -1.08
     både
    -1.04
     coreano
    -1.03
    Said
    -1.02
    contri
    -1.02
    ЧЕ
    -1.02
    РЕ
    -1.02
    turkish
    -1.02
    POSITIVE LOGITS
     on
    0.98
    all
    0.98
     and
    0.96
    old
    0.90
     old
    0.89
    first
    0.88
     as
    0.87
     ,
    0.85
    pl
    0.85
     P
    0.84
    Activations Density 0.066%

    No Known Activations