© 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. 166312
    Prev
    Next
    INDEX
    Explanations

    listing locations and specific items

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

    General quantity measurements

    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
    Surviv
    0.52
    Kunst
    0.47
    筧
    0.47
    Forgot
    0.47
    دون
    0.46
    伤
    0.46
    Czy
    0.46
    舌
    0.46
    Smoothing
    0.45
    天気
    0.45
    POSITIVE LOGITS
     interior
    0.49
     singer
    0.49
     IPCC
    0.49
     cosmos
    0.48
     this
    0.48
     grove
    0.47
     stately
    0.47
     m
    0.47
     CBC
    0.47
     ADE
    0.46
    Activations Density 0.001%

    No Known Activations