© 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. 22-GEMMASCOPE-RES-131K
    7. 32980
    Prev
    Next
    INDEX
    Explanations

    Hebrew and Israel contexts

    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_22/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
     how
    -1.30
    שׂ
    -1.05
     זיי
    -1.02
     ISTAT
    -1.02
    注意
    -1.02
    因为
    -1.02
     ehemaligen
    -1.02
    🦐
    -1.02
    再
    -1.01
     where
    -0.98
    POSITIVE LOGITS
    Hebrew
    1.28
     ד
    1.27
     ב
    1.21
     în
    1.17
    Incluso
    1.16
     ס
    1.12
     ק
    1.06
    ṿ
    1.06
     minimale
    1.05
     מ
    1.04
    Activations Density 0.146%

    No Known Activations