© 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. 10-GEMMASCOPE-RES-131K
    7. 67902
    Prev
    Next
    INDEX
    Explanations

    boolean or CST timezone

    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_10/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
    ৢ
    -1.46
    佧
    -1.45
    orting
    -1.38
    those
    -1.38
    Vtbl
    -1.35
    Those
    -1.34
     celles
    -1.34
     aqueles
    -1.34
    仳
    -1.32
     می‌گوید
    -1.30
    POSITIVE LOGITS
     "
    1.40
     while
    1.20
    nilai
    1.06
     despite
    1.05
     although
    1.03
     échanges
    1.03
     needing
    1.02
    Gum
    1.02
     podczas
    1.01
    漆
    1.00
    Activations Density 0.061%

    No Known Activations