© 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. 105471
    Prev
    Next
    INDEX
    Explanations

    processes, steps, and strategies

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

    steps in order

    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
     राउ
    0.49
     priors
    0.46
     środow
    0.45
     concursos
    0.45
    㔯
    0.44
     zwier
    0.43
     সবার
    0.42
     Analyzer
    0.42
     feste
    0.41
     चुनौतियों
    0.41
    POSITIVE LOGITS
    ка
    0.56
    an
    0.51
    nt
    0.49
    bm
    0.49
    ca
    0.49
    ם
    0.48
    na
    0.48
    cata
    0.46
    bnf
    0.46
    в
    0.45
    Activations Density 0.001%

    No Known Activations