© 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. 19994
    Prev
    Next
    INDEX
    Explanations

    harmful or concerning

    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
     필수
    0.45
     headlights
    0.44
     relentless
    0.44
    гаа
    0.42
    ᆼ
    0.42
     आव
    0.42
     Objekt
    0.42
     आवाज
    0.41
    یا
    0.41
    ਤੇ
    0.41
    POSITIVE LOGITS
    agogue
    0.41
    就不
    0.41
     eluted
    0.41
     甘
    0.40
     antiserum
    0.40
    raten
    0.40
    mock
    0.40
    درسة
    0.40
     baños
    0.40
     effectivement
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.