© 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. 34-GEMMASCOPE-RES-131K
    7. 30523
    Prev
    Next
    INDEX
    Explanations

    grammatical correctness and usage

    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_34/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
    ignored
    -1.01
    の名前
    -0.97
     acides
    -0.94
    ించ
    -0.92
    visionnement
    -0.90
    ^{-}
    -0.90
     pseudonym
    -0.89
     auteurs
    -0.88
     creía
    -0.87
    ateur
    -0.86
    POSITIVE LOGITS
     constructions
    1.45
     gram
    1.34
     grammatical
    1.32
     used
    1.30
     usage
    1.27
     expressing
    1.23
     saying
    1.18
     construction
    1.16
     sentences
    1.15
    使用
    1.14
    Activations Density 0.172%

    No Known Activations