© 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. 88360
    Prev
    Next
    INDEX
    Explanations

    Final GDP or report completion

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

    concepts and contributions

    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
     manne
    0.59
    菪
    0.52
     שני
    0.51
     olma
    0.50
     generics
    0.50
     αντί
    0.49
     hummus
    0.49
    ungi
    0.48
    掝
    0.48
     sexes
    0.48
    POSITIVE LOGITS
    Complete
    0.51
    Excellent
    0.51
    extremely
    0.50
    t
    0.50
    Preparing
    0.49
    issues
    0.49
    Errors
    0.49
    レポート
    0.49
    EM
    0.48
    Rolling
    0.48
    Activations Density 0.001%

    No Known Activations