© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207941
    Prev
    Next
    INDEX
    Explanations

    open world

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

    early stages and subsequent progression

    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
    Negative Logits
    кау
    0.43
     灯
    0.41
    楠
    0.41
     quitar
    0.40
     teórico
    0.40
    中标
    0.39
    规定的
    0.38
    Lamp
    0.37
     ello
    0.37
    ствий
    0.37
    POSITIVE LOGITS
     महे
    0.45
     lorsqu
    0.44
    balances
    0.44
     बैलेंस
    0.43
    ੫
    0.43
     sempat
    0.42
    genic
    0.42
     ensimmä
    0.42
    imah
    0.42
     SMEs
    0.42
    Activations Density 0.001%

    No Known Activations