© 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. 127875
    Prev
    Next
    INDEX
    Explanations

    Chesterfield, Middletown, MIPS, bailout

    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
    t
    -3.63
    蘗
    -2.63
    0
    -2.50
    苹
    -2.50
    ان
    -2.50
     in
    -2.38
     «
    -2.36
     (
    -2.25
     почти
    -2.20
     Rückseite
    -2.20
    POSITIVE LOGITS
     frança
    3.14
     judicia
    3.03
    饹
    3.00
     contribue
    2.94
     riemp
    2.91
    癀
    2.91
     ciasc
    2.86
    мся
    2.84
     ferrovia
    2.83
     sconto
    2.78
    Activations Density 0.012%

    No Known Activations