© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88215
    Prev
    Next
    INDEX
    Explanations

    function that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arrêté
    0.58
    extrait
    0.57
    \{-
    0.55
    ense
    0.55
    pest
    0.54
    rafpunkte
    0.54
    phant
    0.53
    orant
    0.52
    ase
    0.50
    endy
    0.50
    POSITIVE LOGITS
     habría
    0.48
    0.47
    ت
    0.47
     to
    0.46
    כ
    0.46
    ↵↵
    0.46
    真正的
    0.45
    ول
    0.45
     generously
    0.45
     ZH
    0.43
    Activations Density 0.000%

    No Known Activations