© 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. 14751
    Prev
    Next
    INDEX
    Explanations

    list separators and logic

    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
    pueden
    -2.14
    龗
    -2.11
    擽
    -2.08
     récomp
    -2.00
    dienne
    -1.97
     éché
    -1.95
    Однако
    -1.91
     refroid
    -1.91
     MÉ
    -1.90
     FRANCIS
    -1.88
    POSITIVE LOGITS
     in
    2.88
     a
    2.39
     and
    2.31
     shown
    2.20
     have
    2.13
     called
    2.06
     named
    2.05
     become
    2.02
     such
    2.02
     they
    2.02
    Activations Density 0.004%

    No Known Activations