© 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. 14929
    Prev
    Next
    INDEX
    Explanations

    offers and opportunities

    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
     it
    -1.98
     or
    -1.88
     showing
    -1.75
     that
    -1.73
     the
    -1.70
     if
    -1.70
     at
    -1.51
     there
    -1.51
     podczas
    -1.50
     others
    -1.49
    POSITIVE LOGITS
     mauva
    1.66
     hiver
    1.63
     varier
    1.60
     envelo
    1.58
     Chapitre
    1.56
     vanille
    1.56
     prins
    1.55
     hôtel
    1.52
     vinyle
    1.48
     appartement
    1.48
    Activations Density 0.023%

    No Known Activations