© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137064
    Prev
    Next
    INDEX
    Explanations

    fugitive, flee, evade, exile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    篮球
    0.46
     Alcohol
    0.45
     Recycling
    0.44
     Recycle
    0.44
    聋
    0.43
     Grow
    0.42
     recycling
    0.42
     Goose
    0.42
     स्काउट
    0.41
     Kennel
    0.41
    POSITIVE LOGITS
    逃
    0.76
     fugitive
    0.71
     फरार
    0.70
     fled
    0.70
     flee
    0.65
     exile
    0.65
     extradition
    0.65
     fleeing
    0.64
     evade
    0.63
     extrad
    0.62
    Activations Density 0.014%

    No Known Activations