© 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. 234885
    Prev
    Next
    INDEX
    Explanations

    express your own

    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
    ശ്
    0.53
     basaltes
    0.52
    ܝܢ
    0.51
    gheatmap
    0.50
     prendas
    0.50
    ﻓ
    0.50
    ﻫ
    0.50
    تنا
    0.49
    prosperity
    0.49
    ﺗ
    0.49
    POSITIVE LOGITS
    ek
    0.45
     Differences
    0.44
     субъек
    0.42
     ثلاث
    0.42
     thống
    0.40
    先后
    0.40
     পার্থক্য
    0.40
     వివిధ
    0.40
     தமிழ்
    0.40
    FP
    0.40
    Activations Density 0.000%

    No Known Activations