© 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. 22-GEMMASCOPE-RES-131K
    7. 64737
    Prev
    Next
    INDEX
    Explanations

    [Pulse wave velocity]

    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_22/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
     by
    -1.23
     (
    -1.16
     in
    -1.10
    (
    -1.07
     personnalisé
    -1.05
     being
    -1.05
     pegatina
    -1.05
    なのだ
    -1.02
     sympa
    -1.02
    衣服
    -1.01
    POSITIVE LOGITS
    pulseira
    1.25
    Derecho
    1.17
    Hechos
    1.15
    溌
    1.13
     ซึ่ง
    1.12
    Pasos
    1.12
    
    1.11
    Poder
    1.09
    Seguir
    1.09
     یکی
    1.08
    Activations Density 0.002%

    No Known Activations