© 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. 25114
    Prev
    Next
    INDEX
    Explanations

    handle or to

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

    Vigenère chip item monomers Dynamic based distributed

    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
    <0x0D>
    0.52
     Nerve
    0.50
     total
    0.48
     insensitive
    0.48
     effectual
    0.47
     sending
    0.47
     paste
    0.47
     enkel
    0.47
     installer
    0.47
     hernia
    0.47
    POSITIVE LOGITS
    的机会
    0.51
     thiên
    0.49
    民主
    0.48
    的操作
    0.48
    طي
    0.48
    旱
    0.46
    ヒット
    0.46
    λου
    0.45
    ρού
    0.44
    敦煌
    0.44
    Activations Density 0.000%

    No Known Activations