© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49597
    Prev
    Next
    INDEX
    Explanations

    naming or defining using "call" or "term"

    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
    mler
    -0.81
    higer
    -0.79
    toCharArray
    -0.79
     diketahui
    -0.77
    ujete
    -0.77
    ܘ
    -0.76
    áss
    -0.76
    umptions
    -0.75
    看起来
    -0.75
     założ
    -0.75
    POSITIVE LOGITS
     call
    6.09
     calls
    4.75
    call
    4.59
    Call
    4.13
     Call
    3.97
     called
    3.63
    CALL
    3.48
     gọi
    3.44
     calling
    3.44
     CALL
    3.34
    Activations Density 0.129%

    No Known Activations