© 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. 73856
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by verbs or nouns

    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
     was
    -2.20
     who
    -1.70
     but
    -1.58
    詳しくは
    -1.55
     of
    -1.55
     prepares
    -1.48
    を開催
    -1.46
     same
    -1.45
     additionally
    -1.45
     erlä
    -1.44
    POSITIVE LOGITS
    </strong>
    1.78
    купить
    1.76
    廝
    1.75
    _
    1.73
    olog
    1.62
    theless
    1.60
     Nedir
    1.59
    iterranée
    1.59
    вання
    1.59
    uating
    1.59
    Activations Density 0.029%

    No Known Activations