© 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. 40-GEMMASCOPE-2-RES-262K
    7. 111049
    Prev
    Next
    INDEX
    Explanations

    portfolio weights

    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_40_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
    oflu
    0.40
    \{\
    0.39
    季節
    0.39
    inafter
    0.38
    ществует
    0.37
     следу
    0.37
     Stokes
    0.37
    ஞ்சு
    0.37
    asons
    0.37
    নিবেশ
    0.37
    POSITIVE LOGITS
     ム
    0.39
    ुलर
    0.37
    τρα
    0.36
    మూ
    0.35
    kingen
    0.34
    ‎
    0.34
     அட
    0.34
    Someone
    0.34
     سہ
    0.34
     Picnic
    0.34
    Activations Density 0.000%

    No Known Activations