© 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. 44185
    Prev
    Next
    INDEX
    Explanations

    barcode, buffer, BLE, TikTok

    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
     insures
    0.44
     lightweight
    0.43
     हवाले
    0.43
     competitively
    0.42
    ⬯
    0.42
    হত
    0.40
     $(`.
    0.40
     elucidated
    0.40
    ູບ
    0.39
     retracted
    0.39
    POSITIVE LOGITS
    oms
    0.53
    ourt
    0.49
    цен
    0.48
    angas
    0.48
    forms
    0.47
    atypes
    0.47
    ouville
    0.46
     zaken
    0.46
     y
    0.45
    ra
    0.45
    Activations Density 0.000%

    No Known Activations