© 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. 74821
    Prev
    Next
    INDEX
    Explanations

    legal proceedings or statements

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

    computations, safety, unemployment

    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
    जीर
    0.54
    য়ো
    0.49
    宫
    0.47
    য়
    0.47
    宮
    0.46
    겅
    0.46
    পাত
    0.46
    Jose
    0.46
    🤗
    0.46
    Sans
    0.46
    POSITIVE LOGITS
     guarantees
    0.50
     \
    0.49
     Œ
    0.47
    uela
    0.47
     obrig
    0.47
     Fecha
    0.47
     dute
    0.46
    clude
    0.43
     By
    0.43
     ou
    0.43
    Activations Density 0.000%

    No Known Activations