© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111978
    Prev
    Next
    INDEX
    Explanations

    repeat or continuation

    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
     సహాయ
    0.45
     जल
    0.44
     يه
    0.41
     ലഭ
    0.40
     চার
    0.40
    пан
    0.40
     levers
    0.39
    푠
    0.39
     கல்ல
    0.39
     захід
    0.39
    POSITIVE LOGITS
     venezolano
    0.47
    強く
    0.46
     blandt
    0.46
    ියාව
    0.43
     russe
    0.43
     deterioro
    0.43
     dute
    0.42
     Rusia
    0.42
    export
    0.41
    धपुर
    0.41
    Activations Density 0.007%

    No Known Activations