© 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. 61074
    Prev
    Next
    INDEX
    Explanations

    numbers and specific words followed by descriptors

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

    commercial use

    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
    विष्ट
    0.58
    که
    0.53
    ॉड
    0.52
    ब्द
    0.50
    წიფ
    0.50
    უნქ
    0.50
    郫
    0.49
     noyau
    0.48
    ⌵
    0.48
    레스
    0.48
    POSITIVE LOGITS
    0.54
    ry
    0.50
     価格
    0.47
     on
    0.47
    y
    0.46
    aly
    0.45
     Low
    0.45
    alls
    0.45
     LOW
    0.44
     ติด
    0.44
    Activations Density 0.000%

    No Known Activations