© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40061
    Prev
    Next
    INDEX
    Explanations

    fugitive, exile, fled

    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_65k_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
     ধাক
    0.45
    聋
    0.44
     রংপুর
    0.43
    篮球
    0.42
     confusing
    0.41
     स्काउट
    0.41
     swings
    0.40
     빠른
    0.40
     молодо
    0.40
     sadly
    0.39
    POSITIVE LOGITS
     फरार
    0.80
     extradition
    0.80
    逃
    0.79
     fugitive
    0.76
     exile
    0.72
     exiled
    0.71
     fled
    0.71
     extrad
    0.70
     fleeing
    0.66
     flee
    0.63
    Activations Density 0.047%

    No Known Activations