© 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. 132775
    Prev
    Next
    INDEX
    Explanations

    Jewish life and rituals

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

    phrases ending in influence or action

    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
     stumpage
    0.52
     pedagogy
    0.52
     संस्कृत
    0.50
     ১৩২১
    0.49
    ে
    0.49
     ORNL
    0.47
     Thoreau
    0.46
     prioritization
    0.46
     sabbatical
    0.46
     italics
    0.46
    POSITIVE LOGITS
    HandleTypeDef
    0.49
    Poz
    0.45
    gget
    0.43
    inned
    0.43
    élite
    0.42
    Vendo
    0.42
    ducers
    0.42
    scor
    0.41
    狗
    0.41
    dur
    0.39
    Activations Density 0.005%

    No Known Activations