© 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-65K
    4. 10078
    Prev
    Next
    INDEX
    Explanations

    recorded those

    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_65k_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
    ed
    0.55
    ai
    0.52
    funk
    0.47
    am
    0.47
    status
    0.47
    vorm
    0.47
    f
    0.47
    RACT
    0.46
    al
    0.45
    edik
    0.45
    POSITIVE LOGITS
    ིག་
    0.48
     sosten
    0.47
    されており
    0.45
     jobNumber
    0.44
     व्यायाम
    0.44
    過ご
    0.43
    ኛ
    0.43
    ล่า
    0.42
     sustained
    0.42
     %``
    0.42
    Activations Density 0.004%

    No Known Activations