© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168242
    Prev
    Next
    INDEX
    Explanations

    non-english and technical connections

    np_acts-logits-general · gemini-2.5-flash-lite

    snow, rain, and ice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agem
    0.46
    どうぞ
    0.46
    *$
    0.46
    労
    0.45
    수로
    0.44
     Worker
    0.43
    cemment
    0.43
    प्रमाणे
    0.43
    事業
    0.42
    ども
    0.41
    POSITIVE LOGITS
     ဗ
    0.54
     vínculo
    0.53
     صور
    0.52
    »،
    0.49
     الکتر
    0.49
     מק
    0.49
     б
    0.49
     आंगन
    0.48
     בא
    0.48
     huesos
    0.48
    Activations Density 0.001%

    No Known Activations