© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83898
    Prev
    Next
    INDEX
    Explanations

    ** lists, definitions

    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
    ی
    0.50
    ت
    0.48
    gi
    0.46
    GI
    0.42
    راہیم
    0.42
    significant
    0.42
    Crown
    0.42
    growing
    0.41
    \
    0.41
    sail
    0.41
    POSITIVE LOGITS
    大多
    0.42
    怒
    0.42
     {}>,
    0.42
     בי
    0.41
     దగ్
    0.41
     가장
    0.41
     나
    0.40
    ichiro
    0.40
     কারনে
    0.40
     फ्लो
    0.40
    Activations Density 0.008%

    No Known Activations