© 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. 62495
    Prev
    Next
    INDEX
    Explanations

    writing and reading

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

    describingrepresentingholdingcompetenceRole

    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
    올
    0.64
    学家
    0.59
    姗
    0.55
     ferrugineux
    0.53
     étrangères
    0.53
     ennemis
    0.51
    ग्विजय
    0.50
    茨
    0.49
     континен
    0.48
    ія
    0.48
    POSITIVE LOGITS
     Holding
    0.57
     was
    0.52
     Represents
    0.50
     holding
    0.48
     Therapeutics
    0.47
     Holders
    0.47
     Pharmaceuticals
    0.46
     holds
    0.46
     PT
    0.45
     k
    0.45
    Activations Density 0.000%

    No Known Activations