© 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. 102645
    Prev
    Next
    INDEX
    Explanations

    of Jacob, God, Israel

    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
     in
    -1.63
     Their
    -1.39
    rivial
    -1.37
     lèvres
    -1.35
    ).
    -1.35
    ेमाल
    -1.30
    too
    -1.29
    Emple
    -1.28
    >):
    -1.27
    Repositorio
    -1.27
    POSITIVE LOGITS
     הוא
    1.48
     otras
    1.47
     contemporain
    1.34
    sodik
    1.33
    zzarella
    1.33
    <bos>
    1.31
     extrêmement
    1.31
    TemporalType
    1.30
     bary
    1.27
     bambú
    1.27
    Activations Density 0.039%

    No Known Activations