© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11494
    Prev
    Next
    INDEX
    Explanations

    security group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﮧ
    1.72
    ⿳
    1.37
    ాను
    1.33
    idão
    1.31
    taining
    1.28
    ﻢ
    1.28
    푚
    1.28
    ם
    1.27
     సమయంలో
    1.24
    lık
    1.24
    POSITIVE LOGITS
    р
    1.13
     propres
    1.11
    नेश
    1.09
    Под
    1.06
    حية
    1.06
    حي
    1.03
     autres
    1.03
    Printf
    1.02
     вот
    1.02
     hypothetical
    1.01
    Activations Density 0.000%

    No Known Activations