© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100563
    Prev
    Next
    INDEX
    Explanations

    Pronouns followed by verbs

    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
     proposons
    -1.91
    だったが
    -1.68
    天堂
    -1.66
    Ketua
    -1.63
     做
    -1.62
    Televis
    -1.62
     contemporaine
    -1.61
    法国
    -1.61
     even
    -1.59
    原神
    -1.59
    POSITIVE LOGITS
    我真的
    2.05
    </
    1.95
    <em>
    1.81
     núm
    1.81
     OGSÅ
    1.80
    以上です
    1.76
    ς
    1.75
    NUMX
    1.74
    一切都
    1.72
    <blockquote>
    1.65
    Activations Density 0.020%

    No Known Activations