© 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. 40-GEMMASCOPE-2-RES-262K
    7. 28220
    Prev
    Next
    INDEX
    Explanations

    URLs with file paths

    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_40_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
     Badge
    0.45
    뱃
    0.43
    badge
    0.43
     jelen
    0.43
     badge
    0.42
    鲶
    0.42
    嘴
    0.40
     сад
    0.40
    btnInventory
    0.40
     Bender
    0.40
    POSITIVE LOGITS
     empirical
    0.44
    SE
    0.39
    鉞
    0.39
    ওয়
    0.37
    operand
    0.37
    ALLE
    0.37
    pred
    0.36
    empirical
    0.36
    SEE
    0.36
    viol
    0.35
    Activations Density 0.001%

    No Known Activations