© 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. 177805
    Prev
    Next
    INDEX
    Explanations

    insurance discounts

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

    least squares method

    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
    ิ
    0.49
     слід
    0.49
     нему
    0.49
     крайне
    0.48
    лове
    0.48
     прикла
    0.47
     редак
    0.47
     μεγαλύτε
    0.47
    ほど
    0.46
     すぎ
    0.46
    POSITIVE LOGITS
    R
    0.52
    this
    0.44
    participants
    0.44
    source
    0.44
    rett
    0.44
    terminated
    0.44
     this
    0.44
    response
    0.43
    temporary
    0.43
    species
    0.42
    Activations Density 0.000%

    No Known Activations