© 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. 220617
    Prev
    Next
    INDEX
    Explanations

    created, shipped, registered, images

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

    intervene, support, help, walls

    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
    ミリ
    0.52
    英寸
    0.51
     Кня
    0.49
    ಿದ್ದಾನೆ
    0.49
    厘米
    0.48
    上面的
    0.47
    RationalValue
    0.47
    沺
    0.47
     উপরে
    0.47
    在
    0.47
    POSITIVE LOGITS
     игровые
    0.47
     ial
    0.45
     சிங்க
    0.44
     oyn
    0.43
     isLoading
    0.43
     fondo
    0.42
     жүктөө
    0.42
     уйнау
    0.42
     ruang
    0.42
     нее
    0.42
    Activations Density 0.000%

    No Known Activations