© 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. 99920
    Prev
    Next
    INDEX
    Explanations

    descriptions and comments

    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
     音乐
    -0.91
     tornar
    -0.85
    tona
    -0.84
    identific
    -0.84
     Zahlen
    -0.82
    arama
    -0.82
    attu
    -0.81
    identification
    -0.81
     Portail
    -0.80
     согласно
    -0.78
    POSITIVE LOGITS
     description
    3.59
     descriptions
    2.67
    description
    2.64
    Description
    2.58
     Description
    2.53
    setDescription
    2.53
     getDescription
    2.52
    DESCRIPTION
    2.39
    getDescription
    2.36
     DESCRIPTION
    2.22
    Activations Density 0.036%

    No Known Activations