© 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. 29251
    Prev
    Next
    INDEX
    Explanations

    choosing or comparing options

    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
     pasado
    0.46
     concierto
    0.45
     み
    0.43
     Chiche
    0.43
     impor
    0.43
     chuyến
    0.42
     import
    0.42
     shipment
    0.42
     ڈھاکہ
    0.42
     rodeo
    0.42
    POSITIVE LOGITS
    avour
    0.46
    選
    0.43
    輔
    0.42
     favour
    0.40
     favoring
    0.40
    mér
    0.40
    fod
    0.39
    le
    0.39
     controlar
    0.38
     ಆಯ್
    0.38
    Activations Density 0.012%

    No Known Activations