© 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. 148036
    Prev
    Next
    INDEX
    Explanations

    shortest path

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

    loading data, different types

    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
    $.}
    0.55
     crumpled
    0.54
     midpoint
    0.51
     gasket
    0.51
     ladder
    0.50
     gluon
    0.50
     kuin
    0.49
     vez
    0.49
     deiner
    0.49
     vc
    0.49
    POSITIVE LOGITS
    ל
    0.51
     Nonprofit
    0.50
    据悉
    0.49
    荅
    0.47
    豐
    0.47
    📊
    0.47
    丰
    0.46
    兼
    0.46
    𝗵
    0.46
     Microphone
    0.46
    Activations Density 0.000%

    No Known Activations