© 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. 32255
    Prev
    Next
    INDEX
    Explanations

    HTML and code attributes

    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
    יבור
    -0.75
    ङ
    -0.74
     depicts
    -0.70
     vejo
    -0.70
    रु
    -0.69
    QG
    -0.69
    ━━━
    -0.68
    льне
    -0.68
     pública
    -0.67
     香水
    -0.67
    POSITIVE LOGITS
    igshid
    0.66
     cro
    0.65
     wass
    0.65
    stract
    0.64
     cup
    0.64
     Le
    0.64
    iren
    0.63
     alias
    0.63
     parro
    0.63
     Bir
    0.61
    Activations Density 0.060%

    No Known Activations