© 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. 188464
    Prev
    Next
    INDEX
    Explanations

    dates, times, and availability

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

    metaphysical verse, conservative perspective

    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
     peligros
    0.53
     escolas
    0.52
     evi
    0.50
     consape
    0.47
     Datas
    0.47
     опас
    0.46
     observable
    0.46
    嘣
    0.45
     hepatocytes
    0.44
     pericol
    0.44
    POSITIVE LOGITS
    žete
    0.45
    tta
    0.45
    habitation
    0.44
    rystal
    0.43
    都能
    0.43
    `,
    0.42
    `.
    0.42
     campsite
    0.41
     רק
    0.41
    ifice
    0.41
    Activations Density 0.001%

    No Known Activations