© 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. 128724
    Prev
    Next
    INDEX
    Explanations

    risk, crisis, final, five

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

    information and measurements

    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
     certamente
    0.54
     裏
    0.53
     ईमित्र
    0.51
    cD
    0.51
    PRODUCTION
    0.50
    USR
    0.47
     సం
    0.47
    d
    0.46
     героев
    0.46
    Singleton
    0.46
    POSITIVE LOGITS
    ther
    0.46
     Destinations
    0.46
     Strikes
    0.46
     Sexual
    0.45
     Destination
    0.45
    針
    0.44
     astonishing
    0.43
     Lighting
    0.42
    ەش
    0.42
     Conditions
    0.42
    Activations Density 0.000%

    No Known Activations