© 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. 14465
    Prev
    Next
    INDEX
    Explanations

    IE compatibility meta tags

    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
     særlig
    -1.70
     which
    -1.69
     歳
    -1.66
    entistas
    -1.64
     because
    -1.59
    玧
    -1.56
    خیص
    -1.56
    pography
    -1.55
     蕾
    -1.54
    انى
    -1.52
    POSITIVE LOGITS
    1
    2.02
    ,
    1.86
    }
    1.84
    .
    1.77
     I
    1.65
    2
    1.64
    3
    1.59
    )
    1.55
     solche
    1.53
     &
    1.52
    Activations Density 0.010%

    No Known Activations