© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1142
    Prev
    Next
    INDEX
    Explanations

    revocable, scrutinizes, permalink, indemnified

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

    prefixes leading to common suffixes

    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_53_width_65k_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
     खूबस
    0.21
    ujjati
    0.21
    𐰇
    0.21
     المحاضره
    0.21
    chyné
    0.21
    ্টর
    0.20
    𐰖
    0.20
    ীদের
    0.20
     Balliye
    0.20
     দর্শকের
    0.20
    POSITIVE LOGITS
    </strong>
    0.24
    .’”
    0.22
    .”.
    0.19
    <eos>
    0.18
    a
    0.18
    а
    0.18
    pro
    0.18
    −
    0.18
    ـ
    0.18
    ↵↵↵
    0.18
    Activations Density 0.257%

    No Known Activations