© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13542
    Prev
    Next
    INDEX
    Explanations

    TV shows and channels

    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_10/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
    s
    -2.13
     but
    -1.60
    
    -1.59
     crafted
    -1.57
    ího
    -1.52
    既然
    -1.48
    ”.
    -1.48
     of
    -1.43
    も行
    -1.43
     entirely
    -1.40
    POSITIVE LOGITS
    кос
    1.59
     journaliste
    1.56
     wartości
    1.53
    🧐
    1.53
     "
    1.49
    derdag
    1.44
    л
    1.44
    ῞
    1.42
     lignes
    1.42
     Livre
    1.41
    Activations Density 0.036%

    No Known Activations