© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118187
    Prev
    Next
    INDEX
    Explanations

    starts specific phrases

    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
    भी
    -0.73
    Strategic
    -0.73
    Swim
    -0.72
     cloning
    -0.71
     COV
    -0.71
    ضای
    -0.68
    享受
    -0.68
    梁
    -0.68
     låg
    -0.67
    Khan
    -0.67
    POSITIVE LOGITS
     createState
    0.70
     Mass
    0.70
     bulk
    0.69
     பி
    0.69
    ples
    0.68
    ErrorResponse
    0.68
    lox
    0.67
     Post
    0.66
     Last
    0.66
     Near
    0.65
    Activations Density 0.049%

    No Known Activations