© 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. 33429
    Prev
    Next
    INDEX
    Explanations

    dance parties

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

    identifying specific entities or actions

    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
    k
    0.53
    jt
    0.51
     Action
    0.49
     Instrument
    0.48
     Around
    0.46
    ktx
    0.46
     Avenue
    0.44
     Ass
    0.43
    Action
    0.43
     Report
    0.43
    POSITIVE LOGITS
     hogs
    0.52
     trei
    0.50
     boar
    0.47
    まあ
    0.47
     papá
    0.46
     attacked
    0.46
    參
    0.46
     চাল
    0.45
     gak
    0.45
     glav
    0.45
    Activations Density 0.000%

    No Known Activations