© 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. 92973
    Prev
    Next
    INDEX
    Explanations

    communicative actions and descriptions

    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
    вли
    0.48
    М
    0.46
    Т
    0.46
    йн
    0.46
    Dynamics
    0.46
    م
    0.45
    ТИ
    0.45
    (
    0.45
    тим
    0.43
    рые
    0.43
    POSITIVE LOGITS
     interviewed
    0.48
     ও
    0.48
    हिनी
    0.46
     गठन
    0.45
     opened
    0.44
     Communications
    0.44
     કરતા
    0.44
     กำ
    0.44
     pulled
    0.44
     heard
    0.43
    Activations Density 0.000%

    No Known Activations