© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-65K
    4. 670
    Prev
    Next
    INDEX
    Explanations

    agreement followed by specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
     I
    0.81
    ।
    0.77
    <0x0D>
    0.74
     skapa
    0.70
    ?
    0.69
    ،
    0.68
     barre
    0.65
    </h3>
    0.63
     filament
    0.63
     capillaries
    0.63
    POSITIVE LOGITS
    on
    1.44
    as
    1.03
    GA
    0.90
    RO
    0.88
    ES
    0.87
    EN
    0.86
    ON
    0.86
     జాగ్ర
    0.86
    KI
    0.82
    谨慎
    0.82
    Activations Density 2.077%

    No Known Activations