© 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. 94
    Prev
    Next
    INDEX
    Explanations

    ):

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

    code syntax

    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
     breasts
    0.37
     {-
    0.35
     {
    0.34
     {{\
    0.33
    蒽
    0.32
    кування
    0.32
     STEELS
    0.32
    農
    0.32
    圯
    0.32
    埝
    0.32
    POSITIVE LOGITS
    ;}
    0.60
    []}
    0.54
    }.
    0.52
    !}
    0.46
    .}
    0.45
    </div>
    0.45
     }
    0.44
    +}
    0.42
    if
    0.42
    ?}
    0.42
    Activations Density 0.000%

    No Known Activations