© 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. 96576
    Prev
    Next
    INDEX
    Explanations

    loss arising from

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

    specialized contexts

    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
    /*
    0.56
    originally
    0.55
    /*'
    0.54
    formerly
    0.50
    ream
    0.50
    ou
    0.49
    cosmos
    0.48
    fontSize
    0.48
     antiguas
    0.47
    //
    0.46
    POSITIVE LOGITS
     mảnh
    0.52
     linemen
    0.50
     sath
    0.45
     salespeople
    0.44
     hag
    0.44
    陝
    0.42
     Masyarakat
    0.42
     finance
    0.41
     ligaments
    0.41
     salesmen
    0.41
    Activations Density 0.000%

    No Known Activations