© 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. 90094
    Prev
    Next
    INDEX
    Explanations

    advance the, secondary platform, practice exams, lined with

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

    questions and phrases

    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
    arie
    0.46
    tragung
    0.45
    zym
    0.45
    🥊
    0.45
    alion
    0.44
    aty
    0.43
    Escape
    0.43
     प्रतीक
    0.43
     Escape
    0.41
    MVCProject
    0.41
    POSITIVE LOGITS
    listen
    0.49
    USR
    0.45
    ‌ర
    0.44
    等於
    0.44
    ِلِّ
    0.44
     নির্ম
    0.43
    ્રોલ
    0.43
    ﻠ
    0.43
    ាតុ
    0.42
    should
    0.42
    Activations Density 0.000%

    No Known Activations