© 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. 53597
    Prev
    Next
    INDEX
    Explanations

    clarify what things refer to

    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
    ne
    0.49
     I
    0.45
    shiny
    0.43
     .,
    0.42
     Kid
    0.41
    คุณ
    0.41
    蓉
    0.41
     อิ
    0.41
    你会
    0.40
     Ili
    0.40
    POSITIVE LOGITS
     purchasers
    0.47
     requester
    0.46
     subiect
    0.45
    恺
    0.45
    ត្រូវ
    0.45
     curricula
    0.45
     modalidades
    0.45
     incluyen
    0.44
     permitan
    0.44
     permiten
    0.44
    Activations Density 0.001%

    No Known Activations