© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136241
    Prev
    Next
    INDEX
    Explanations

    positions and roles

    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_31_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
    尿
    0.44
    ంబే
    0.42
     मतदार
    0.40
    لقه
    0.40
    ध्यक्ष
    0.39
     Holz
    0.39
     Kampf
    0.39
     करतो
    0.39
     Narcotics
    0.39
    再
    0.38
    POSITIVE LOGITS
    ot
    0.55
    ન
    0.53
    itr
    0.52
    iton
    0.49
    ỵ
    0.47
    idding
    0.46
    adr
    0.46
     verificar
    0.46
    i
    0.45
    ị
    0.45
    Activations Density 0.003%

    No Known Activations