© 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. 88328
    Prev
    Next
    INDEX
    Explanations

    dates and specific requirements

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

    movement, Modern, inspired, harvesting, While, needs

    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
     kilometer
    0.46
    눴
    0.46
     juga
    0.45
     kilometre
    0.45
    Ų
    0.44
     foolproof
    0.43
     forfeit
    0.43
     astray
    0.43
    たくさん
    0.43
    kilometer
    0.43
    POSITIVE LOGITS
     phục
    0.46
    something
    0.46
     edt
    0.45
     संज्ञा
    0.45
    一项
    0.44
     //.
    0.44
     существуют
    0.43
    应用的
    0.43
    सामान्यीकृत
    0.42
     dotyczą
    0.42
    Activations Density 0.001%

    No Known Activations