© 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. 58987
    Prev
    Next
    INDEX
    Explanations

    Dr. followed by name

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

    Dr. followed by a name

    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
    зил
    0.45
    Colonel
    0.43
    ଠ
    0.43
    дый
    0.42
    URED
    0.41
     streetlight
    0.41
    Drain
    0.41
     silic
    0.41
    ছিলেন
    0.40
    ﺪ
    0.39
    POSITIVE LOGITS
    ing
    0.73
    ia
    0.64
    ة
    0.63
    ne
    0.62
    a
    0.62
    us
    0.61
    ik
    0.59
    za
    0.58
    ك
    0.56
    ac
    0.54
    Activations Density 0.015%

    No Known Activations