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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1949
    Prev
    Next
    INDEX
    Explanations

    Amikacin ending quarters

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

    keycloak

    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
    🧂
    0.33
    㣱
    0.31
    𝙋
    0.30
    ंधर
    0.30
     एंटर
    0.30
    上涨
    0.30
    ➟
    0.30
    踽
    0.29
    Mâc
    0.29
    䐂
    0.29
    POSITIVE LOGITS
    im
    0.37
    end
    0.34
    s
    0.33
    remarks
    0.31
    os
    0.30
     bra
    0.30
    ime
    0.29
    aps
    0.29
    all
    0.29
    version
    0.29
    Activations Density 0.110%

    No Known Activations