© 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. 10-GEMMASCOPE-RES-131K
    7. 14750
    Prev
    Next
    INDEX
    Explanations

    Harbor, canceled, signaling, traveling

    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
     troublesome
    -2.52
    ...:
    -2.45
    en
    -2.39
     ``
    -2.39
    ––
    -2.38
     hassle
    -2.34
    ൎ
    -2.34
     maxim
    -2.34
     minim
    -2.31
     summar
    -2.31
    POSITIVE LOGITS
    ſty
    2.53
    
    2.41
    葙
    2.38
     商务
    2.34
    "}}>
    2.33
    栳
    2.28
    ї
    2.23
     オブ
    2.19
    身影
    2.19
    leggio
    2.17
    Activations Density 0.316%

    No Known Activations