© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 204
    Prev
    Next
    INDEX
    Explanations

    information following verbs

    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
     one
    -1.25
     outside
    -1.18
     between
    -1.15
     a
    -1.15
     more
    -1.13
    したが
    -1.10
    Our
    -1.09
     cubre
    -1.08
     in
    -1.07
     vuelve
    -1.07
    POSITIVE LOGITS
     this
    2.64
     این
    2.03
     these
    1.84
    この
    1.74
     the
    1.59
    這個
    1.59
    這
    1.45
    这
    1.41
    这些
    1.40
     dieser
    1.39
    Activations Density 0.035%

    No Known Activations