© 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. 199484
    Prev
    Next
    INDEX
    Explanations

    Chinese policy, accessible by

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

    Prompt Engineering

    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
     '=
    0.42
    Equipment
    0.41
    mqtt
    0.41
    ent
    0.41
    \|=
    0.41
    queryString
    0.40
     निभा
    0.40
    ವುದ
    0.40
    ObjectMapper
    0.39
    '&&
    0.39
    POSITIVE LOGITS
     behest
    0.52
     summer
    0.50
    lerinde
    0.50
     profond
    0.48
     প্রজন্মের
    0.48
    夏の
    0.48
     evrops
    0.47
     verano
    0.47
     trimester
    0.47
    夏
    0.47
    Activations Density 0.001%

    No Known Activations