© 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. 109025
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
    ┙
    -0.78
     ആ
    -0.77
    BaseUrl
    -0.75
     عربي
    -0.74
    Milliseconds
    -0.73
    eses
    -0.73
    obt
    -0.73
    isChecked
    -0.72
     jusque
    -0.71
    malo
    -0.71
    POSITIVE LOGITS
     hace
    2.72
     לפני
    2.44
     منذ
    2.06
    Hace
    2.05
     ago
    1.98
    年前
    1.89
     قبل
    1.81
     last
    1.70
     πριν
    1.68
     Hace
    1.66
    Activations Density 0.021%

    No Known Activations