© 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. 232188
    Prev
    Next
    INDEX
    Explanations

    entity pairings

    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
    フ
    0.49
    ак
    0.48
    п
    0.47
    ্প
    0.45
    스크
    0.45
    த்துள்ள
    0.44
    я
    0.44
    те
    0.43
    프
    0.43
    흐
    0.43
    POSITIVE LOGITS
     ouro
    0.50
     God
    0.50
     Gottes
    0.49
     hatte
    0.48
     विधान
    0.48
     kann
    0.48
     treffen
    0.48
     vene
    0.48
     antiserum
    0.47
    ien
    0.47
    Activations Density 0.000%

    No Known Activations