© 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. 72460
    Prev
    Next
    INDEX
    Explanations

    franz or johann followed by names

    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
    -2.63
    '
    -2.59
     Verständ
    -2.48
     beliebtesten
    -2.34
    al
    -2.28
     By
    -2.28
     häufigsten
    -2.23
     a
    -2.22
     That
    -2.16
    ;
    -2.09
    POSITIVE LOGITS
     نکرد
    2.64
    鸯
    2.52
     alpine
    2.50
    ⭏
    2.45
     bedeckt
    2.36
    ቼ
    2.36
    CHREIB
    2.33
    Ꮞ
    2.31
    놋
    2.31
    ksamkeit
    2.27
    Activations Density 0.005%

    No Known Activations