© 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. 83860
    Prev
    Next
    INDEX
    Explanations

    to be

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

    concepts and workflows

    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
     (
    0.44
     fairly
    0.42
    己
    0.41
    द्वारा
    0.40
    分
    0.40
     プリント
    0.40
     আলোকে
    0.39
    dataFile
    0.39
    airplane
    0.38
     הפר
    0.38
    POSITIVE LOGITS
    kring
    0.55
    🤑
    0.53
     veulent
    0.49
    ächlich
    0.47
    旖
    0.47
     vzt
    0.47
    🎗
    0.47
    👾
    0.46
     भावनात्मक
    0.46
    🖕
    0.46
    Activations Density 0.002%

    No Known Activations