© 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. 108517
    Prev
    Next
    INDEX
    Explanations

    wikipedia links

    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
    ँ
    -0.79
     czyli
    -0.76
    owanie
    -0.75
     limits
    -0.73
    𝙚
    -0.72
    veil
    -0.71
     analyses
    -0.71
     cricketer
    -0.71
    試合
    -0.71
     projects
    -0.71
    POSITIVE LOGITS
    wikipedia
    1.13
    expanded
    0.84
     Wikipedia
    0.79
    Wikipedia
    0.75
    ◥
    0.74
     protagonista
    0.74
    を入力
    0.73
     Landis
    0.73
    . 
    0.73
     amist
    0.73
    Activations Density 0.006%

    No Known Activations