© 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. 198389
    Prev
    Next
    INDEX
    Explanations

    safety, last, private, tags, assets

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

    chatbots, cells, or persons

    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
    ر
    0.57
    gene
    0.53
    bo
    0.52
    gle
    0.50
    R
    0.50
    zone
    0.49
    vio
    0.49
    bl
    0.48
    suit
    0.48
    wear
    0.48
    POSITIVE LOGITS
    腖
    0.54
    ાન
    0.53
    ﻧ
    0.51
    쐞
    0.50
    әр
    0.49
     उत्साह
    0.47
    囟
    0.46
     sahaja
    0.46
     olhar
    0.45
     संसाधन
    0.45
    Activations Density 0.000%

    No Known Activations