© 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. 11164
    Prev
    Next
    INDEX
    Explanations

    English fragments

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

    various languages and scripts

    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
    ยนต์
    0.49
    '
    0.49
     y
    0.48
     reflet
    0.47
     احد
    0.47
    ς
    0.47
     இருந்து
    0.46
     projet
    0.46
     ordena
    0.46
     with
    0.46
    POSITIVE LOGITS
    ang
    0.64
    un
    0.54
    ud
    0.54
    🉑
    0.51
    id
    0.50
    ad
    0.48
    ir
    0.46
    .
    0.46
    im
    0.46
    ub
    0.46
    Activations Density 0.084%

    No Known Activations