© 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. 223904
    Prev
    Next
    INDEX
    Explanations

    foreign languages, concepts, or names

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

    by means of

    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
    у
    0.53
    DEFAULT
    0.47
    Mack
    0.47
     Мак
    0.47
     Mack
    0.46
    s
    0.43
     э
    0.43
    wig
    0.43
     T
    0.42
     क
    0.42
    POSITIVE LOGITS
     apparaître
    0.64
     prévenir
    0.52
    庚
    0.52
     množství
    0.52
     attraverso
    0.48
    ικοί
    0.48
     accueillir
    0.48
    ရန်
    0.48
     έναν
    0.48
     ciò
    0.47
    Activations Density 0.000%

    No Known Activations