© 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. 44990
    Prev
    Next
    INDEX
    Explanations

    names starting with André

    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
    at
    -3.27
    section
    -2.92
     ‘
    -2.70
    </b>
    -2.67
    me
    -2.63
     l
    -2.63
    co
    -2.44
    an
    -2.27
    on
    -2.25
     a
    -2.20
    POSITIVE LOGITS
     欣赏
    3.13
    ércio
    2.88
    lossians
    2.77
     laquelle
    2.67
    齎
    2.66
    鯓
    2.63
    鰲
    2.58
     Arquitectura
    2.55
     輕
    2.52
    The
    2.48
    Activations Density 0.007%

    No Known Activations