© 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. 25733
    Prev
    Next
    INDEX
    Explanations

    Bigg, Q, March, In

    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
    踔
    -1.41
    歟
    -1.33
    之时
    -1.25
    筚
    -1.22
     Visita
    -1.20
     chré
    -1.16
     åren
    -1.15
     ruinous
    -1.15
     wymaga
    -1.15
     السياس
    -1.15
    POSITIVE LOGITS
     deportivas
    1.52
    alucía
    1.44
     tonight
    1.40
    ituation
    1.34
     group
    1.34
     estratég
    1.32
    ervant
    1.30
     everyone
    1.28
    öpfe
    1.27
     pidió
    1.26
    Activations Density 0.005%

    No Known Activations