© 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. 106594
    Prev
    Next
    INDEX
    Explanations

    from various locations

    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
     it
    -1.23
     if
    -1.03
    <bos>
    -1.00
     function
    -0.99
     and
    -0.98
    ↵↵↵↵
    -0.98
    नी
    -0.98
    h
    -0.96
    ilo
    -0.96
     someone
    -0.96
    POSITIVE LOGITS
     across
    2.88
     around
    2.56
     abroad
    1.74
     throughout
    1.67
     backgrounds
    1.62
     outside
    1.52
     elsewhere
    1.48
    across
    1.48
     verschillende
    1.47
     afar
    1.46
    Activations Density 0.048%

    No Known Activations