© 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. 128515
    Prev
    Next
    INDEX
    Explanations

    Arabic and Hebrew words

    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
     It
    -3.42
    There
    -2.80
     This
    -2.80
    It
    -2.58
    </h2>
    -2.36
     there
    -2.28
     There
    -2.17
    This
    -2.08
    These
    -2.05
     After
    -2.02
    POSITIVE LOGITS
     them
    2.33
     that
    2.22
    謌
    1.98
    沨
    1.98
     the
    1.95
    崀
    1.91
    omics
    1.89
     forKey
    1.88
     atau
    1.87
    咥
    1.87
    Activations Density 0.005%

    No Known Activations