© 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. 115690
    Prev
    Next
    INDEX
    Explanations

    aluminium foil

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

    complicated aspect ratio

    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
     판매
    0.49
     หน้า
    0.48
    žem
    0.47
     한다
    0.47
     Thế
    0.47
     October
    0.46
     몇
    0.46
     เว
    0.46
     노래
    0.46
     음
    0.46
    POSITIVE LOGITS
    由
    0.52
    getNext
    0.46
    を与
    0.46
    newToken
    0.46
    明確
    0.46
    素
    0.46
    બ
    0.45
    入
    0.44
    snippet
    0.44
    まず
    0.43
    Activations Density 0.000%

    No Known Activations