© 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. 238015
    Prev
    Next
    INDEX
    Explanations

    this form; Civil War; body must

    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
    getWidth
    0.52
     PropTypes
    0.49
    that
    0.48
     Unters
    0.47
    even
    0.47
     japonicus
    0.46
     Ρ
    0.46
    kappa
    0.46
    sealed
    0.45
    密封
    0.45
    POSITIVE LOGITS
     disposal
    0.46
    Û
    0.46
     دنیا
    0.46
    GYPT
    0.46
     bestow
    0.45
     sanction
    0.44
     judgment
    0.44
    indahan
    0.43
     detriment
    0.42
     जगत
    0.42
    Activations Density 0.001%

    No Known Activations