© 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. 59666
    Prev
    Next
    INDEX
    Explanations

    indexes and supplemental terms

    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
    閙
    -2.95
     were
    -2.81
    ),
    -2.59
    呖
    -2.59
    之为
    -2.45
    饜
    -2.45
    鲼
    -2.44
    
    -2.42
    摃
    -2.41
    OUTUBE
    -2.34
    POSITIVE LOGITS
    </h4>
    2.61
    a
    2.36
    同じ
    2.34
    m
    2.27
    ‘
    2.23
    },
    2.23
     exceeding
    2.20
    
    2.16
    鈇
    2.14
    それ
    2.13
    Activations Density 0.009%

    No Known Activations