© 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. 10094
    Prev
    Next
    INDEX
    Explanations

    surface types and traction

    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
     anual
    -1.23
     fotbal
    -1.21
    ’
    -1.17
    THEY
    -1.16
    </strong>
    -1.16
     Anſ
    -1.13
    ]=(
    -1.11
    }}$
    -1.10
    maske
    -1.09
    )));
    -1.09
    POSITIVE LOGITS
     especially
    1.32
     particularly
    1.25
     навіть
    1.24
     conditions
    1.24
     zealous
    1.13
     even
    1.13
    شاركة
    1.13
     powinna
    1.11
     teils
    1.07
     Bardzo
    1.07
    Activations Density 0.050%

    No Known Activations