© 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. 238591
    Prev
    Next
    INDEX
    Explanations

    APP Download

    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
    regions
    0.52
    以色列
    0.51
    Э
    0.51
    次元
    0.49
    制度
    0.49
    gefunden
    0.48
    풀
    0.47
    確認
    0.47
    धा
    0.46
    申
    0.46
    POSITIVE LOGITS
     Entertainment
    0.54
    umon
    0.53
     Kant
    0.52
     kame
    0.51
    avic
    0.50
     Court
    0.50
     Slider
    0.49
    axanthin
    0.48
    ang
    0.48
     perspective
    0.47
    Activations Density 0.000%

    No Known Activations