© 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. 128952
    Prev
    Next
    INDEX
    Explanations

    short initial words

    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
     and
    -3.86
     which
    -3.19
     of
    -2.23
     που
    -2.17
    fordshire
    -2.16
    »
    -2.02
    ="
    -2.02
    hetically
    -1.96
    wości
    -1.93
     using
    -1.90
    POSITIVE LOGITS
     posando
    2.19
     It
    2.13
     hilfreich
    2.08
    
    2.06
     promocional
    2.05
     comunica
    1.99
     entrando
    1.98
    \
    1.98
     justamente
    1.98
     Another
    1.98
    Activations Density 0.004%

    No Known Activations