© 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. 138801
    Prev
    Next
    INDEX
    Explanations

    non-English mentions

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

    usually a, preferred the

    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
     fetches
    0.50
     ejec
    0.47
    盾
    0.46
    ิจ
    0.44
     shield
    0.41
     tathapi
    0.41
     fetched
    0.40
     blaster
    0.40
     rač
    0.40
     battles
    0.40
    POSITIVE LOGITS
     Yên
    0.57
    m
    0.56
     উল্লেখ
    0.54
    ColumnKind
    0.51
     Nói
    0.51
    𝗠
    0.48
    شهر
    0.48
     येऊ
    0.47
    tLogRow
    0.47
    tell
    0.46
    Activations Density 0.000%

    No Known Activations