© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 174982
    Prev
    Next
    INDEX
    Explanations

    new guard, typical type, function allows

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

    herbaceous plant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    メリ
    0.49
    ativo
    0.48
    h
    0.47
    ?
    0.46
    uriken
    0.44
    f
    0.43
    aggable
    0.43
    ﾘ
    0.43
    ༽
    0.42
     σο
    0.41
    POSITIVE LOGITS
     Hourly
    0.49
     Clothes
    0.49
     Correlations
    0.48
     Hours
    0.48
     interpretar
    0.48
     Interpretation
    0.47
     Rescue
    0.47
     Stunde
    0.47
    ловой
    0.47
    LastGenOutput
    0.47
    Activations Density 0.001%

    No Known Activations