© 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. 46605
    Prev
    Next
    INDEX
    Explanations

    page followed by verb

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

    resource conversion maximization

    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
    J
    0.44
    Han
    0.41
    Dm
    0.40
    H
    0.40
    maan
    0.40
    D
    0.39
    P
    0.39
    _+
    0.39
    한
    0.38
    han
    0.37
    POSITIVE LOGITS
     campsites
    0.50
    ீக
    0.49
    ্বিক
    0.49
     Genoa
    0.46
     quaisquer
    0.45
    ywidual
    0.45
    த்தைப்
    0.44
     প্রক্রিয়া
    0.44
     Cincinnati
    0.44
     poisons
    0.44
    Activations Density 0.003%

    No Known Activations