© 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. 38679
    Prev
    Next
    INDEX
    Explanations

    foundational planning

    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
     "*************"
    0.48
    ത്
    0.46
     cél
    0.45
     പ്രവർത്തന
    0.44
     وګټ
    0.44
     joie
    0.43
    autoarima
    0.43
     especializado
    0.43
    வ்
    0.42
    ರೋ
    0.42
    POSITIVE LOGITS
     occasions
    0.46
     a
    0.42
    ries
    0.42
    leness
    0.42
    ৭
    0.42
    rawing
    0.41
    思考
    0.40
    års
    0.40
     <
    0.39
     suppressing
    0.39
    Activations Density 0.003%

    No Known Activations