© 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. 58979
    Prev
    Next
    INDEX
    Explanations

    future events and outcomes

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

    endless hunger, memories, data, deserves honesty

    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
    银
    0.49
    欧元
    0.48
     қили
    0.47
    erto
    0.46
     слід
    0.46
    建筑物
    0.46
     সুদর্শন
    0.45
    毌
    0.45
    烣
    0.45
    hombre
    0.44
    POSITIVE LOGITS
     njeg
    0.52
    и
    0.47
     */}
    0.46
     stray
    0.45
     fileprivate
    0.44
     zajed
    0.44
     prace
    0.43
    )},
    0.42
     displ
    0.42
     oun
    0.42
    Activations Density 0.000%

    No Known Activations