© 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. 44117
    Prev
    Next
    INDEX
    Explanations

    under a condition

    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
    '
    -3.34
    五年
    -2.55
    ☏
    -2.39
     was
    -2.30
    ?"
    -2.20
    饽
    -2.16
    淬
    -2.14
    ichteten
    -2.11
    ться
    -2.09
    Y
    -2.09
    POSITIVE LOGITS
     the
    2.75
    ︲
    2.61
    歃
    2.55
    Dengan
    2.52
    
    2.45
    0
    2.38
    魠
    2.38
    透過
    2.34
     với
    2.33
     wth
    2.31
    Activations Density 0.055%

    No Known Activations