© 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. 107645
    Prev
    Next
    INDEX
    Explanations

    function f

    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
     FESTIVAL
    -0.82
    FEST
    -0.82
    VSS
    -0.81
     Festival
    -0.81
     Futbol
    -0.79
    生素
    -0.78
    fault
    -0.77
     scott
    -0.75
    festival
    -0.75
    faculty
    -0.75
    POSITIVE LOGITS
     f
    2.63
    f
    1.86
     function
    1.77
     func
    1.77
     g
    1.63
     fun
    1.61
     functions
    1.61
     F
    1.57
    varphi
    1.54
     функ
    1.35
    Activations Density 0.158%

    No Known Activations