© 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. 29675
    Prev
    Next
    INDEX
    Explanations

    research and explanations

    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
    م
    0.47
    思想
    0.46
    平衡
    0.45
     사고
    0.44
    中毒
    0.44
    Glas
    0.44
    釹
    0.44
    blockquote
    0.43
     Slight
    0.41
    ಸ್ಥ
    0.41
    POSITIVE LOGITS
    t
    0.78
    r
    0.54
    s
    0.50
    al
    0.47
    ̆
    0.44
    currentSprite
    0.43
     saque
    0.42
     testify
    0.42
     onFailure
    0.42
     punte
    0.42
    Activations Density 0.001%

    No Known Activations