© 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. 13241
    Prev
    Next
    INDEX
    Explanations

    apache libraries

    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
     punctatis
    0.48
     róż
    0.48
     crows
    0.48
     ყ
    0.47
     químicas
    0.46
    ین
    0.46
     intervalos
    0.46
    lardır
    0.45
     Omphalodes
    0.45
     epile
    0.45
    POSITIVE LOGITS
    6
    0.43
    Logged
    0.43
     convenience
    0.41
    い
    0.41
    阿
    0.41
    mail
    0.40
     CH
    0.40
    Ray
    0.40
    社
    0.40
    cache
    0.39
    Activations Density 0.009%

    No Known Activations