© 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. 165205
    Prev
    Next
    INDEX
    Explanations

    require major

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

    based on factors

    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
    ę
    0.43
    を作
    0.42
     Sentinel
    0.40
     Coin
    0.39
     LCS
    0.39
    Attempt
    0.38
     Runway
    0.38
    5
    0.38
     Prairie
    0.37
    冈
    0.37
    POSITIVE LOGITS
     ACTIONS
    0.42
     اكيد
    0.41
    <unused67>
    0.38
     comigo
    0.38
     బీజేపీ
    0.38
     مكان
    0.38
    managerpage
    0.38
     boots
    0.38
     actions
    0.38
     ساتھ
    0.37
    Activations Density 0.000%

    No Known Activations