© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58938
    Prev
    Next
    INDEX
    Explanations

    URLs and addresses

    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
     a
    -1.63
     certain
    -1.61
    峄
    -1.47
    </sub>
    -1.41
     haremos
    -1.40
    }
    -1.38
     both
    -1.35
    ())
    -1.34
     şi
    -1.30
     });
    
    -1.30
    POSITIVE LOGITS
    Their
    1.63
    Biografi
    1.45
     даже
    1.37
     notare
    1.32
    Fakta
    1.30
     bija
    1.28
    這些
    1.27
    Todas
    1.24
    ('
    1.23
     ihrer
    1.23
    Activations Density 0.084%

    No Known Activations