© 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. 22-GEMMASCOPE-RES-131K
    7. 9395
    Prev
    Next
    INDEX
    Explanations

    specific context or attribute

    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
     Our
    -1.23
     nachts
    -1.16
    БО
    -1.16
     feront
    -1.16
    aia
    -1.14
     tiende
    -1.13
     хворо
    -1.10
     of
    -1.09
     després
    -1.08
    नि
    -1.07
    POSITIVE LOGITS
    resizingMask
    1.45
    signable
    1.42
    〝
    1.41
     that
    1.41
    Zubereitung
    1.39
    筧
    1.36
     experiences
    1.34
     mechanisms
    1.32
    signee
    1.31
    !"
    1.30
    Activations Density 0.042%

    No Known Activations