© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124227
    Prev
    Next
    INDEX
    Explanations

    product codes or part numbers

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

    hexadecimal or code identifiers

    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_31_width_262k_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
    Nếu
    0.40
     मींस
    0.40
    Choice
    0.39
    নেস
    0.39
    Erin
    0.39
    服务
    0.38
    KET
    0.38
    𝓎
    0.38
     किरा
    0.38
    选择
    0.38
    POSITIVE LOGITS
     winters
    0.38
     hydrate
    0.38
     dl
    0.38
    toHaveBeen
    0.38
     involuntarily
    0.36
     লে
    0.36
     Lisboa
    0.36
    fusion
    0.35
     outputPath
    0.35
     delegado
    0.35
    Activations Density 0.051%

    No Known Activations