© 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. 57106
    Prev
    Next
    INDEX
    Explanations

    HTML Transitional DOCTYPE

    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
    lineHeight
    -0.79
    ']).
    -0.72
    indari
    -0.71
    حياته
    -0.70
    vantages
    -0.69
     hosszú
    -0.69
    ंह
    -0.69
     rostros
    -0.68
    रीर
    -0.68
    ']);
    -0.68
    POSITIVE LOGITS
     Gerä
    0.74
    atist
    0.72
     Том
    0.72
     Serie
    0.70
     negligent
    0.69
    ᴇ
    0.66
    智慧
    0.66
    ပ
    0.65
     futebol
    0.65
    ่า
    0.64
    Activations Density 0.046%

    No Known Activations