© 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. 1561
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    colleagues, weight, and numbers

    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
    ⱪ
    0.39
     ছাড়াও
    0.38
     नाइट्रोजन
    0.37
     lymphoid
    0.36
     democracia
    0.36
    ńskie
    0.35
     polícia
    0.35
     vậy
    0.34
    ानीय
    0.34
     ilişkin
    0.34
    POSITIVE LOGITS
    ด
    0.44
    0.39
    サ
    0.36
    サン
    0.36
    وست
    0.36
    d
    0.36
    <em>
    0.35
     วิ
    0.34
    liess
    0.34
    고
    0.34
    Activations Density 0.000%

    No Known Activations