© 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. 22-GEMMASCOPE-RES-131K
    7. 35415
    Prev
    Next
    INDEX
    Explanations

    substring, split, path components

    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_22/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
     territ
    -1.09
    Życiorys
    -0.95
     Lokales
    -0.92
     atlik
    -0.86
    faatkan
    -0.86
    ')
    -0.85
    录取
    -0.81
     apreciar
    -0.81
    UIImage
    -0.80
     Confederate
    -0.79
    POSITIVE LOGITS
     مرة
    0.96
     Coyle
    0.95
     udało
    0.89
     phthalate
    0.84
     hlavy
    0.82
    guson
    0.81
     prévoir
    0.81
     aislados
    0.80
     getLocation
    0.79
     Crear
    0.79
    Activations Density 0.009%

    No Known Activations