© 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. 86075
    Prev
    Next
    INDEX
    Explanations

    no charge

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

    yellow envelope

    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
     I
    0.50
     N
    0.50
     II
    0.50
     SPACE
    0.49
    space
    0.49
     Space
    0.48
     Vineyard
    0.48
     regions
    0.48
     V
    0.47
     A
    0.47
    POSITIVE LOGITS
     unjustly
    0.55
     잘못
    0.52
    ണമെന്ന്
    0.51
    考试
    0.50
    Aluno
    0.49
    泄
    0.49
     স্ত্রীর
    0.48
    Despatx
    0.48
     এতটাই
    0.48
    GetUser
    0.48
    Activations Density 0.000%

    No Known Activations