© 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. 7823
    Prev
    Next
    INDEX
    Explanations

    terms of

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

    in terms of

    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
    geq
    0.57
    ។
    0.57
    .}
    0.56
    4
    0.56
    9
    0.56
    eight
    0.54
    ।"
    0.53
    ".
    0.52
    और
    0.52
    كَ
    0.52
    POSITIVE LOGITS
     of
    0.86
    ของการ
    0.79
    នៃ
    0.71
     של
    0.70
     của
    0.67
    ของ
    0.62
     ऑफ
    0.61
     των
    0.56
    ’
    0.55
    ى
    0.55
    Activations Density 0.386%

    No Known Activations