© 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. 44826
    Prev
    Next
    INDEX
    Explanations

    arguments passed when

    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
    id
    0.57
    ika
    0.50
     Ю
    0.47
    小說
    0.46
    ки
    0.46
    IU
    0.46
    nYou
    0.46
     메뉴
    0.46
    ⿴
    0.46
    燈
    0.45
    POSITIVE LOGITS
    -{\
    0.50
    Swiss
    0.48
    ருக்கு
    0.45
    infer
    0.43
     punched
    0.43
     അഭി
    0.41
    ването
    0.41
     precisamente
    0.40
    тацию
    0.40
     punctured
    0.39
    Activations Density 0.000%

    No Known Activations