© 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. 100019
    Prev
    Next
    INDEX
    Explanations

    entity attributes

    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
    </h5>
    -1.70
     giyim
    -1.36
    ".
    -1.24
     пришел
    -1.23
     pathetic
    -1.20
     delicious
    -1.20
     Eigentü
    -1.18
    Cuen
    -1.18
    ni
    -1.17
    蘩
    -1.16
    POSITIVE LOGITS
     to
    1.63
    <bos>
    1.62
    хол
    1.38
    czył
    1.38
    terness
    1.26
    TestingModule
    1.24
    炬
    1.19
    
    1.19
    菖
    1.18
    韬
    1.17
    Activations Density 0.438%

    No Known Activations