© 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. 194714
    Prev
    Next
    INDEX
    Explanations

    people and questions

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

    foreign language text

    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
     or
    0.50
     &/
    0.49
    你去
    0.44
     algéb
    0.43
     établissements
    0.42
    ,
    0.40
     jeweils
    0.40
     procédés
    0.40
     [
    0.39
     edilir
    0.39
    POSITIVE LOGITS
    ен
    0.55
    ение
    0.51
    வுடன்
    0.50
    вої
    0.48
     অনেক
    0.47
    ер
    0.47
     घातक
    0.47
     המש
    0.46
    ANIM
    0.46
     ワン
    0.45
    Activations Density 0.000%

    No Known Activations