© 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. 128567
    Prev
    Next
    INDEX
    Explanations

    information, devices, gas, nothing

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

    worn, been, disputes, list, naturaleza

    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
    ल
    0.55
    ک
    0.54
     Financial
    0.53
    ade
    0.52
    ans
    0.51
    ko
    0.49
    koop
    0.49
    wall
    0.49
    ion
    0.48
    work
    0.48
    POSITIVE LOGITS
    )：
    0.54
     հ
    0.50
    ുവ
    0.49
     théorème
    0.49
    隣
    0.49
     extrémités
    0.48
     znamen
    0.48
    ρωση
    0.48
    gramModel
    0.47
     guill
    0.47
    Activations Density 0.001%

    No Known Activations