© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103001
    Prev
    Next
    INDEX
    Explanations

    code separators and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReturnType
    -0.70
    ⏩
    -0.69
    낫
    -0.67
    grass
    -0.65
    agine
    -0.65
    paren
    -0.65
     الشم
    -0.65
    ContentLoaded
    -0.64
    navigationItem
    -0.63
     vorbe
    -0.63
    POSITIVE LOGITS
    στά
    0.75
    ះ
    0.71
    މ
    0.67
     ràng
    0.65
    JPN
    0.64
    orov
    0.64
     簡
    0.64
     sensation
    0.64
     cầm
    0.63
     erwähnt
    0.63
    Activations Density 0.064%

    No Known Activations