© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 31951
    Prev
    Next
    INDEX
    Explanations

    making you think

    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
    ^{*}}\
    0.41
    swürdig
    0.39
    !!");
    0.39
    </h3>
    0.38
    !");
    0.38
    quinone
    0.38
    !!!");
    0.38
     ಕೇಳ
    0.38
    ...");
    0.37
    öy
    0.37
    POSITIVE LOGITS
     approaches
    0.48
     platforms
    0.48
     broad
    0.48
     deeper
    0.47
     broadening
    0.47
     receding
    0.46
     advances
    0.45
     améliorer
    0.45
     emerging
    0.43
     reformers
    0.42
    Activations Density 0.001%

    No Known Activations