© 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. 164939
    Prev
    Next
    INDEX
    Explanations

    measurements and lists

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

    specifying roles or names in lists

    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
    °
    0.52
    .
    0.51
    ז
    0.50
    ?
    0.49
    らない
    0.47
    â
    0.47
    ק
    0.47
    점을
    0.46
    ***
    0.45
    ρ
    0.45
    POSITIVE LOGITS
     создал
    0.54
     Flughafen
    0.54
     penduduk
    0.51
     Köz
    0.51
     ආරක්ෂ
    0.51
     Sólo
    0.50
     cambió
    0.50
     দাশ
    0.48
    кугӀ
    0.48
     Mön
    0.48
    Activations Density 0.000%

    No Known Activations