© 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. 164378
    Prev
    Next
    INDEX
    Explanations

    "biopsy" or "attempt" followed by punctuation

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

    specifying types of things

    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
     發
    0.52
    ník
    0.49
    吸收
    0.48
    র
    0.46
    ル
    0.45
    lero
    0.44
     connexes
    0.43
     পর্দ
    0.43
    分别
    0.43
    ampilkan
    0.43
    POSITIVE LOGITS
     Pharmacy
    0.46
     Sandwich
    0.45
     Encyclopedia
    0.45
    Knowledge
    0.44
    Objective
    0.43
    Ƅ
    0.43
    Third
    0.43
    ٔ
    0.43
     दुसऱ्या
    0.43
     Sling
    0.42
    Activations Density 0.002%

    No Known Activations