© 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. 198341
    Prev
    Next
    INDEX
    Explanations

    descriptive topics from texts

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

    programming, math, and software concepts

    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
    最早
    0.53
    찬
    0.52
     razón
    0.50
     系统
    0.50
    گوید
    0.49
    Otra
    0.48
    ँची
    0.48
    노
    0.48
    ሰራ
    0.47
     temprana
    0.47
    POSITIVE LOGITS
     શિક્ષણ
    0.49
    ü
    0.49
    jLabel
    0.49
     reside
    0.48
    ui
    0.46
    ij
    0.45
    um
    0.44
    DSP
    0.44
     கல்லூ
    0.44
    ia
    0.43
    Activations Density 0.000%

    No Known Activations