© 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. 40732
    Prev
    Next
    INDEX
    Explanations

    why we, based on

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

    corporate security, combine 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
     outcome
    0.41
    一つ
    0.41
    転職
    0.41
    京
    0.40
    何度
    0.39
     overthrown
    0.39
     downright
    0.39
     ಅದೇ
    0.39
    🫢
    0.39
     surprising
    0.38
    POSITIVE LOGITS
    pex
    0.45
    mount
    0.44
    ində
    0.41
     scriv
    0.41
    Max
    0.40
    esty
    0.40
     juni
    0.40
    clud
    0.39
    mark
    0.39
    valuer
    0.39
    Activations Density 0.000%

    No Known Activations