© 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. 135244
    Prev
    Next
    INDEX
    Explanations

    completion and progression

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

    topic role context

    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
    н
    0.54
     M
    0.50
    一
    0.50
     Muda
    0.47
    т
    0.47
     virtuelle
    0.45
    лия
    0.45
     Z
    0.44
    Traité
    0.44
     patrón
    0.43
    POSITIVE LOGITS
     μέχρι
    0.49
     σχε
    0.48
     בין
    0.43
    까지
    0.43
    addSprite
    0.42
    ওয়া
    0.42
     cộng
    0.42
    ওয়া
    0.41
    sendKeyDown
    0.41
    uhi
    0.41
    Activations Density 0.000%

    No Known Activations