© 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. 10-GEMMASCOPE-RES-131K
    7. 42654
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    carus
    -1.73
     sogenannte
    -1.67
    providedIn
    -1.66
    jenige
    -1.65
    簠
    -1.63
    Apesar
    -1.56
     sitten
    -1.45
     either
    -1.45
     verbess
    -1.45
     acontec
    -1.45
    POSITIVE LOGITS
     and
    2.81
    6
    1.70
    8
    1.58
    7
    1.54
    2
    1.51
     will
    1.47
    3
    1.41
    5
    1.35
    1
    1.26
    ↵↵
    1.25
    Activations Density 0.071%

    No Known Activations