© 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. 245157
    Prev
    Next
    INDEX
    Explanations

    Reserved site IDs

    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
    鄢
    0.56
    住院
    0.55
    阁
    0.51
    বৃত্তি
    0.49
    ἓ
    0.48
    财产
    0.48
    增加了
    0.47
    헙
    0.46
    峰
    0.46
    还能
    0.45
    POSITIVE LOGITS
     shark
    0.53
     Ather
    0.52
     PROCESS
    0.52
     Wright
    0.49
     Warr
    0.49
     Sharks
    0.47
     Chichester
    0.47
     Wicklow
    0.47
     Plac
    0.46
    shark
    0.46
    Activations Density 0.001%

    No Known Activations