© 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. 130677
    Prev
    Next
    INDEX
    Explanations

    comparison, process, elements

    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
     ingenting
    -1.34
     største
    -1.26
     juft
    -1.21
     oeil
    -1.20
     fuper
    -1.20
     œil
    -1.19
     alltid
    -1.18
    yeron
    -1.16
     feveral
    -1.13
     précédents
    -1.13
    POSITIVE LOGITS
     Audiodateien
    1.59
    Formats
    1.45
     TextAlign
    1.26
     дошко
    1.23
     formato
    1.19
     Benefits
    1.18
    formats
    1.17
     format
    1.16
     usada
    1.16
     feedback
    1.16
    Activations Density 0.031%

    No Known Activations