© 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. 2896
    Prev
    Next
    INDEX
    Explanations

    items for sale

    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
     Thessal
    -0.82
    MANAGEMENT
    -0.75
     transparence
    -0.72
    З
    -0.71
    Multiplication
    -0.71
    Kru
    -0.71
    Blas
    -0.70
    UGAR
    -0.69
     बजाय
    -0.69
    znac
    -0.69
    POSITIVE LOGITS
     sale
    6.06
    sale
    4.78
     Sale
    4.59
    Sale
    4.34
     SALE
    3.92
    SALE
    3.44
     venta
    2.14
     Verkauf
    2.09
     sales
    2.05
     purchase
    2.03
    Activations Density 0.047%

    No Known Activations