© 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. 155457
    Prev
    Next
    INDEX
    Explanations

    athlete competes

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

    food lists and categories

    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
    á
    0.62
    hydro
    0.51
    agro
    0.51
    asjonen
    0.51
    aal
    0.50
    fer
    0.50
    獸
    0.49
    icl
    0.49
    ︎
    0.49
     Dei
    0.48
    POSITIVE LOGITS
     sparks
    0.56
     casts
    0.53
     evidences
    0.52
     inescap
    0.50
     crosses
    0.49
     brackets
    0.47
     shouts
    0.47
     sword
    0.46
     noodles
    0.46
     swords
    0.46
    Activations Density 0.001%

    No Known Activations