© 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. 163270
    Prev
    Next
    INDEX
    Explanations

    event names and names

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

    react, cloth, elements, cat

    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
    בו
    0.42
    唢
    0.42
    뭉
    0.41
     Gonz
    0.41
    ნობ
    0.41
     substrings
    0.39
    rän
    0.39
    Bracketing
    0.39
    桎
    0.39
    Archivo
    0.38
    POSITIVE LOGITS
     आनंद
    0.55
     exciting
    0.48
     beautiful
    0.46
     forced
    0.46
     feeble
    0.45
    ydı
    0.45
    тур
    0.45
    !:
    0.45
     was
    0.44
    ということ
    0.44
    Activations Density 0.000%

    No Known Activations