© 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. 236205
    Prev
    Next
    INDEX
    Explanations

    specific types or categories

    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
    rụ
    0.46
    秞
    0.45
    epy
    0.44
     крас
    0.44
    ́n
    0.43
    ärg
    0.42
     LaTeX
    0.42
     输出
    0.42
    flops
    0.42
    uj
    0.41
    POSITIVE LOGITS
    ﻢ
    0.48
     averaging
    0.46
    HUS
    0.42
    ங்கும்
    0.41
    normals
    0.40
     approximating
    0.40
     arrivals
    0.40
     Hilde
    0.40
    PAss
    0.39
    Lif
    0.39
    Activations Density 0.001%

    No Known Activations