© 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. 15914
    Prev
    Next
    INDEX
    Explanations

    names with code and punctuation

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

    The neuron is essentially dead—it does not reliably activate on any tokens and thus doesn’t detect any particular pattern.

    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
    Already
    -1.16
     bezpeč
    -1.12
    still
    -1.09
     súčas
    -1.05
    gün
    -1.02
    already
    -1.01
     tecnologias
    -1.00
    الأ
    -0.99
    =[[
    -0.99
     próprias
    -0.98
    POSITIVE LOGITS
    ército
    1.05
    3
    0.98
    2
    0.94
    delse
    0.94
    clave
    0.93
    8
    0.91
    ússia
    0.91
    derry
    0.89
     habl
    0.88
     Sadly
    0.87
    Activations Density 0.001%

    No Known Activations