© 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. 26224
    Prev
    Next
    INDEX
    Explanations

    words following certain conjunctions or nouns

    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
     gebeten
    -1.60
    hability
    -1.57
    ("/:
    -1.56
     effectuer
    -1.46
     ouvrir
    -1.45
    aneity
    -1.41
    eliness
    -1.38
    зывы
    -1.37
    bės
    -1.36
     aidé
    -1.34
    POSITIVE LOGITS
     in
    1.70
     or
    1.60
     at
    1.54
     apparently
    1.39
     their
    1.38
     these
    1.38
     supposedly
    1.36
     many
    1.30
     both
    1.30
     quite
    1.28
    Activations Density 0.332%

    No Known Activations