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

    Neuronpedia

    Jacobian LensNEW
    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. 23515
    Prev
    Next
    INDEX
    Explanations

    modal verbs and intent

    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
     Gardens
    0.59
    瘓
    0.54
     içerisinde
    0.53
     जल
    0.52
     Permissions
    0.52
     Trafford
    0.51
     yapı
    0.51
     Beaches
    0.50
     monies
    0.50
     Populate
    0.50
    POSITIVE LOGITS
    ≒
    0.70
    benzoimidazole
    0.65
     antioxid
    0.61
     hoge
    0.61
    geqq
    0.61
     rougeâtre
    0.60
    Japanese
    0.59
     일본
    0.59
    ㎛
    0.59
     abnormality
    0.57
    Activations Density 0.019%

    No Known Activations