© 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. 3966
    Prev
    Next
    INDEX
    Explanations

    special characters and diverse languages

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

    structured lists and notes

    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
     tí
    0.38
    財務
    0.37
     intestin
    0.37
     FINANCIAL
    0.37
     دوا
    0.37
     جائے
    0.36
    SegmentInfo
    0.36
    鰭
    0.36
     nage
    0.35
    rocin
    0.35
    POSITIVE LOGITS
    <0x0D>
    0.45
    等着
    0.41
     தினமும்
    0.39
    配备
    0.38
     উপদে
    0.38
     funcionan
    0.38
    Если
    0.37
     कलर
    0.36
    ிழமை
    0.36
     использу
    0.36
    Activations Density 0.001%

    No Known Activations