© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 97916
    Prev
    Next
    INDEX
    Explanations

    download below

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

    However, while, hopefully

    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
    대가
    0.47
    ై
    0.46
    撳
    0.46
    라면
    0.44
     объек
    0.44
    ગો
    0.44
    बड़े
    0.43
     সজ্জিত
    0.43
    냐면
    0.43
    吉
    0.43
    POSITIVE LOGITS
     Vertreter
    0.49
     polymorphism
    0.47
     Schwann
    0.47
     Intermediate
    0.47
     tropos
    0.45
     Studenten
    0.44
    ন্থ
    0.44
     intermedia
    0.44
     Theatre
    0.43
     Polym
    0.42
    Activations Density 0.002%

    No Known Activations