© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 701
    Prev
    Next
    INDEX
    Explanations

    math notation and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    end
    -2.84
     Both
    -2.61
     Even
    -2.23
     perpetually
    -2.19
     Getting
    -2.19
     vehemently
    -2.14
     EVERY
    -2.09
    もともと
    -2.09
     undeniably
    -2.08
     strangely
    -2.00
    POSITIVE LOGITS
    ⩴
    2.19
     interessante
    2.13
    these
    2.06
    during
    2.06
     Dinas
    2.03
     صفحۀ
    2.00
     実例
    1.98
    酲
    1.97
    this
    1.91
    they
    1.88
    Activations Density 0.013%

    No Known Activations