© 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. 39851
    Prev
    Next
    INDEX
    Explanations

    is a boolean

    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
    
    -1.25
     INE
    -1.20
     fhall
    -1.19
    神
    -1.19
     praticamente
    -1.19
     firft
    -1.18
     Municipalidad
    -1.16
     放題
    -1.16
     パーカー
    -1.15
    一丝
    -1.14
    POSITIVE LOGITS
     a
    2.38
     an
    1.95
     both
    1.75
     our
    1.70
     from
    1.67
     or
    1.39
     it
    1.38
     bereits
    1.34
     its
    1.32
     good
    1.32
    Activations Density 0.060%

    No Known Activations