© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86959
    Prev
    Next
    INDEX
    Explanations

    Metal, Nate, or errors

    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
    [
    -2.23
    9
    -2.08
    2
    -1.95
    The
    -1.88
    <h3>
    -1.88
    It
    -1.87
    1
    -1.86
    3
    -1.80
     varandra
    -1.79
    6
    -1.78
    POSITIVE LOGITS
     and
    2.39
     including
    2.05
     such
    1.65
    ;}
    
    1.56
     a
    1.51
     during
    1.49
    注意事
    1.47
     drau
    1.47
    damen
    1.46
     laim
    1.43
    Activations Density 0.000%

    No Known Activations