© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30234
    Prev
    Next
    INDEX
    Explanations

    starting from

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

    log(numeric value) or currency

    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
     lern
    0.44
     ispit
    0.43
     respond
    0.42
     inflater
    0.42
     teat
    0.42
     //'
    0.41
     pew
    0.40
    𝓢
    0.40
     teach
    0.40
     energ
    0.40
    POSITIVE LOGITS
    longrightarrow
    0.45
    犮
    0.43
    customer
    0.43
    expenses
    0.42
    겠지만
    0.42
     ብዙ
    0.41
     totaling
    0.41
    খানা
    0.41
    ច្រើន
    0.41
    rizioni
    0.41
    Activations Density 0.000%

    No Known Activations