© 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. 34-GEMMASCOPE-RES-131K
    7. 87131
    Prev
    Next
    INDEX
    Explanations

    code documentation or comments

    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_34/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
     particularly
    -0.86
     in
    -0.84
     to
    -0.81
     quite
    -0.79
     as
    -0.75
     never
    -0.74
    ulitan
    -0.74
     (
    -0.74
    这就是
    -0.74
     really
    -0.74
    POSITIVE LOGITS
    üyada
    1.00
    visuel
    0.91
    Begriffsklä
    0.91
     моей
    0.87
     prachtige
    0.86
    ⁇
    0.85
    škas
    0.84
     Mexique
    0.84
     betere
    0.84
     Espagne
    0.83
    Activations Density 0.068%

    No Known Activations