© 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. 120059
    Prev
    Next
    INDEX
    Explanations

    ability or option

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

    how to choose

    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
    우
    0.52
    থা
    0.49
     출
    0.48
    eraj
    0.48
    㖵
    0.47
     구간
    0.46
    Ст
    0.45
     모두
    0.45
    TRANS
    0.45
     ਨਾਲ
    0.45
    POSITIVE LOGITS
     aquella
    0.60
     aile
    0.50
     aquell
    0.48
     tears
    0.45
     wept
    0.44
    jl
    0.43
     collocation
    0.43
     Familie
    0.42
     Gua
    0.42
     Array
    0.41
    Activations Density 0.001%

    No Known Activations