© 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. 134776
    Prev
    Next
    INDEX
    Explanations

    torvastatin

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

    following growth enhances specific

    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
    d
    0.67
    trans
    0.59
    environmental
    0.58
    de
    0.58
    all
    0.57
    fair
    0.55
    Federal
    0.55
    t
    0.55
    or
    0.55
    from
    0.55
    POSITIVE LOGITS
     stupid
    0.55
     Stupid
    0.50
     desolate
    0.50
     volontà
    0.50
     fark
    0.49
     drunken
    0.49
     forza
    0.48
     cittadini
    0.48
     questa
    0.47
     potenza
    0.47
    Activations Density 0.000%

    No Known Activations