© 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. 181499
    Prev
    Next
    INDEX
    Explanations

    various preparations and beginnings

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

    lists and enumerations

    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
    й
    0.43
    始终
    0.42
    с
    0.40
     завжди
    0.40
    ー
    0.38
    ჩ
    0.38
    ând
    0.37
    ynı
    0.37
    茥
    0.37
    Ani
    0.37
    POSITIVE LOGITS
     allerlei
    0.55
     preparar
    0.51
     pripre
    0.48
     इंट्रो
    0.45
     pre
    0.44
     elaborar
    0.43
     berbagai
    0.43
     inaugural
    0.42
     introd
    0.42
     preparing
    0.42
    Activations Density 0.001%

    No Known Activations