© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 23873
    Prev
    Next
    INDEX
    Explanations

    Chinatown, car wash, Business Insider, walks of life

    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
    selbe
    -2.47
    其他
    -2.22
    If
    -2.20
    When
    -2.14
    where
    -2.05
    ꒳
    -2.05
    是
    -2.02
     Schluß
    -1.98
     vorigen
    -1.91
    As
    -1.91
    POSITIVE LOGITS
    </strong>
    2.20
    逦
    2.11
    isation
    2.11
    柃
    2.09
     jugar
    2.06
    titial
    2.06
    didSet
    2.03
    
    2.03
     familie
    2.03
    nement
    2.03
    Activations Density 0.007%

    No Known Activations