© 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. 44241
    Prev
    Next
    INDEX
    Explanations

    search queries and code

    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
     विडियो
    0.59
     स्क्रिप्ट
    0.57
     ভরণ
    0.54
     जहाज़
    0.53
    <unused497>
    0.53
     खोलने
    0.53
    ^{*}=\
    0.52
     సహాయ
    0.52
     मॉक
    0.52
     영상을
    0.51
    POSITIVE LOGITS
    عت
    0.55
    in
    0.41
     and
    0.41
     crush
    0.40
    ű
    0.40
    م
    0.40
    íč
    0.39
    ન
    0.39
    pool
    0.39
     plain
    0.39
    Activations Density 0.000%

    No Known Activations