© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 341
    Prev
    Next
    INDEX
    Explanations

    low-, high-, single- prefixes

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

    short or open compound adjectives

    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
     mumkin
    0.22
    abbanti
    0.21
    <unused2173>
    0.20
     Shaping
    0.20
     BEING
    0.20
    áus
    0.20
    ensitive
    0.19
    recent
    0.19
     अभिन्न
    0.19
     بنائیں
    0.19
    POSITIVE LOGITS
    handedly
    0.41
    -
    0.39
    handed
    0.38
     handed
    0.33
    liners
    0.32
    headed
    0.31
    hearted
    0.31
     sided
    0.31
     hearted
    0.29
    footed
    0.29
    Activations Density 1.021%

    No Known Activations