© 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. 91745
    Prev
    Next
    INDEX
    Explanations

    file path manipulation

    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
     stehe
    -0.76
     getKey
    -0.75
    сторо
    -0.73
     recevez
    -0.71
    jącym
    -0.70
     TAG
    -0.69
    Fmt
    -0.68
    кина
    -0.68
     BODY
    -0.68
     plástica
    -0.68
    POSITIVE LOGITS
    path
    1.36
     path
    1.18
     pictureBox
    0.85
     ребенку
    0.85
     étan
    0.84
     offensichtlich
    0.83
    fällen
    0.83
    ٬
    0.82
    PathVariable
    0.82
    KAN
    0.82
    Activations Density 0.003%

    No Known Activations