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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71254
    Prev
    Next
    INDEX
    Explanations

    leading into descriptions

    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_262k_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
    viamente
    0.49
     然后
    0.49
    itzar
    0.47
    !;
    0.46
     ancak
    0.46
     אך
    0.46
    ractic
    0.45
    మ్యాచ్
    0.45
     మరియు
    0.44
     agus
    0.44
    POSITIVE LOGITS
    ከተ
    0.44
    лт
    0.43
     Chicago
    0.43
    ت
    0.42
     Ext
    0.40
     சந்த
    0.40
    ත්
    0.39
     добро
    0.39
    滚
    0.39
     handful
    0.39
    Activations Density 0.008%

    No Known Activations