© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70261
    Prev
    Next
    INDEX
    Explanations

    to something

    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
    I
    -2.50
     by
    -2.19
    <h2>
    -2.05
    -2.05
        
    -2.03
    (
    -2.00
     When
    -1.95
    #
    -1.88
    :
    -1.84
    <
    -1.77
    POSITIVE LOGITS
    茈
    2.27
    豨
    2.22
     墊
    2.13
    ㌘
    2.09
    螃
    2.08
    摃
    1.96
    曁
    1.93
     favoritas
    1.92
    decoración
    1.91
     撮り
    1.88
    Activations Density 0.023%

    No Known Activations