© 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. 77391
    Prev
    Next
    INDEX
    Explanations

    defining functions or methods

    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
     marah
    -0.92
    낼
    -0.82
     promen
    -0.82
    JAJA
    -0.81
    RICIA
    -0.81
     vétérina
    -0.79
    seamnă
    -0.79
     belles
    -0.77
     chauff
    -0.77
    гии
    -0.77
    POSITIVE LOGITS
     func
    4.47
    func
    3.94
     function
    2.44
     fun
    2.08
    FUNC
    1.97
    Func
    1.93
     functions
    1.91
     функ
    1.91
     functional
    1.82
     FUNC
    1.79
    Activations Density 0.055%

    No Known Activations