© 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. 5941
    Prev
    Next
    INDEX
    Explanations

    initialisms within parentheses

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

    initialisms in parentheses

    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
     njega
    0.42
     ہ
    0.41
     هغه
    0.41
     entonces
    0.40
     परंतु
    0.40
    描写
    0.40
     audiov
    0.40
     č
    0.39
     آن
    0.38
     സ
    0.38
    POSITIVE LOGITS
    which
    0.41
    USD
    0.41
    provides
    0.40
    Insp
    0.39
    This
    0.39
    f
    0.38
    TS
    0.38
    About
    0.37
    ATS
    0.37
    hoog
    0.37
    Activations Density 0.029%

    No Known Activations