© 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. 173171
    Prev
    Next
    INDEX
    Explanations

    profile writing

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

    profileinputgroupexpandcut

    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
    ടന
    0.53
     ဝ
    0.50
     unwarranted
    0.49
     tuss
    0.46
     ၀
    0.45
    แหล่ง
    0.44
     demurrer
    0.42
     interruption
    0.42
     inade
    0.42
     inappropri
    0.41
    POSITIVE LOGITS
    .*;
    0.50
    .
    0.48
    ella
    0.48
    strftime
    0.46
    chio
    0.46
    ñón
    0.45
    iriman
    0.45
     Glide
    0.45
     পুলিশের
    0.45
    gha
    0.44
    Activations Density 0.001%

    No Known Activations