© 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. 90197
    Prev
    Next
    INDEX
    Explanations

    Russia abolished

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

    requires attunement

    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
    ឈ្មោះ
    0.52
    زين
    0.50
    PartResult
    0.47
    grou
    0.47
    LOADING
    0.47
    >]
    0.46
    seekers
    0.45
    丳
    0.45
    భర
    0.44
    EXIT
    0.44
    POSITIVE LOGITS
     rented
    0.54
     kunci
    0.51
     fortified
    0.51
     visit
    0.49
     courses
    0.49
     redemption
    0.49
     motherhood
    0.49
     filed
    0.48
     secara
    0.48
     notified
    0.48
    Activations Density 0.000%

    No Known Activations