© 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. 86539
    Prev
    Next
    INDEX
    Explanations

    places and research

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

    academics and diplomas

    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
    ými
    0.53
    igenschaften
    0.51
    züge
    0.49
     nimi
    0.48
    blätter
    0.48
    aliment
    0.47
    igheder
    0.47
    恕
    0.47
    封闭
    0.46
     ámbito
    0.45
    POSITIVE LOGITS
     Shanks
    0.47
    ARY
    0.47
     academics
    0.46
    ATED
    0.45
     %>',
    0.45
    だけでも
    0.45
    ICKS
    0.44
    UNK
    0.43
    ADER
    0.43
     акаде
    0.43
    Activations Density 0.000%

    No Known Activations