© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118825
    Prev
    Next
    INDEX
    Explanations

    parentheses or brackets followed by content

    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
     perdón
    -0.89
    を行いました
    -0.88
    …).
    -0.88
    ).....
    -0.88
    مكن
    -0.86
    াপ
    -0.86
    ⁉
    -0.86
     preto
    -0.85
     if
    -0.85
     on
    -0.84
    POSITIVE LOGITS
     |
    1.37
     [+
    1.33
     Explained
    1.31
     explained
    1.30
     updated
    1.27
     [&
    1.26
     [
    1.26
    updated
    1.25
     พร้อม
    1.20
    explained
    1.18
    Activations Density 0.057%

    No Known Activations