© 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. 5739
    Prev
    Next
    INDEX
    Explanations

    worth out, not always, dependent

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

    experimental writing

    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
     we
    0.46
     values
    0.44
     our
    0.43
     t
    0.40
    classification
    0.40
     הש
    0.40
     Surface
    0.39
     features
    0.39
     Howell
    0.39
     То
    0.38
    POSITIVE LOGITS
     رياضيات
    0.52
    '})
    0.48
     matem
    0.44
    ેશન
    0.44
    ᇂ
    0.43
    ienced
    0.43
    WithFieldContext
    0.43
    ِين
    0.42
    错了
    0.42
    LastGen
    0.41
    Activations Density 0.000%

    No Known Activations