© 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. 79627
    Prev
    Next
    INDEX
    Explanations

    collection and personal use

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

    how to use

    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
    '
    0.62
    まずは
    0.54
     depositors
    0.52
     victimes
    0.49
    ניות
    0.47
    Includes
    0.47
    Bulletin
    0.44
     examining
    0.44
     vineyards
    0.43
     frescos
    0.43
    POSITIVE LOGITS
    am
    0.49
    解
    0.47
    hoe
    0.47
    iec
    0.46
    ie
    0.46
    forte
    0.45
     Hoe
    0.45
    imped
    0.45
    sum
    0.45
     cháu
    0.44
    Activations Density 0.000%

    No Known Activations