© 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. 99438
    Prev
    Next
    INDEX
    Explanations

    SELECT usage

    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
     When
    -2.47
    Perhaps
    -2.20
    While
    -2.14
    Because
    -2.09
     If
    -2.08
    Generally
    -2.08
    When
    -2.06
    Like
    -2.05
    Surprisingly
    -2.03
    Some
    -2.00
    POSITIVE LOGITS
     \
    2.48
    
    2.27
    \
    2.19
     dando
    2.06
    睃
    1.98
    "
    1.95
     différents
    1.91
    𓆏
    1.88
    nearly
    1.84
    zaSy
    1.83
    Activations Density 0.013%

    No Known Activations