© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63890
    Prev
    Next
    INDEX
    Explanations

    sending keys

    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
    oric
    -0.77
     ഒരു
    -0.72
    స్
    -0.71
    تهم
    -0.71
    nda
    -0.71
    dulos
    -0.70
     ESTIM
    -0.69
     校
    -0.69
     potrebbero
    -0.69
    onStart
    -0.69
    POSITIVE LOGITS
    sendKeys
    1.46
     clears
    1.39
     typing
    1.38
    CLEAR
    1.36
    clear
    1.32
     Keys
    1.28
     cleared
    1.26
    输入
    1.24
     clearing
    1.24
     clear
    1.23
    Activations Density 0.008%

    No Known Activations