© 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. 44929
    Prev
    Next
    INDEX
    Explanations

    places people live

    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
    </b>
    -1.27
    .</
    -1.22
    nt
    -1.21
    껏
    -1.21
     fiducia
    -1.19
     they
    -1.17
     любы
    -1.17
     نداره
    -1.16
     люди
    -1.14
     sindaco
    -1.13
    POSITIVE LOGITS
     would
    1.30
    ผม
    1.25
    ’
    1.20
    isTrue
    1.18
     residences
    1.17
    เรา
    1.16
    лтемелер
    1.16
    
    1.15
    คน
    1.14
    新浪
    1.14
    Activations Density 0.091%

    No Known Activations