© 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. 107233
    Prev
    Next
    INDEX
    Explanations

    programming function/method declarations

    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
     snob
    -0.85
    спорта
    -0.82
    Fuentes
    -0.80
     infractions
    -0.79
     scegliere
    -0.78
    Provin
    -0.77
     frets
    -0.77
    Adic
    -0.77
     电影
    -0.76
     fraudul
    -0.75
    POSITIVE LOGITS
     foo
    1.70
    foo
    1.45
     func
    1.34
     test
    1.26
     fun
    1.24
     method
    1.16
     say
    1.16
     some
    1.09
    TestMethod
    1.08
    method
    1.05
    Activations Density 0.071%

    No Known Activations