© 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. 100903
    Prev
    Next
    INDEX
    Explanations

    introduces speculation or hypothesis

    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
    趿
    -2.95
    婞
    -2.84
     felpa
    -2.67
    鉭
    -2.61
    𓐍
    -2.58
    をあ
    -2.47
     tuta
    -2.42
    ”（
    -2.41
    ことができます
    -2.39
    ......”
    -2.36
    POSITIVE LOGITS
    .
    3.16
     Also
    2.73
     Which
    2.64
    pecabe
    2.52
     \
    2.52
     contain
    2.47
    (
    2.42
    那就
    2.41
     .
    2.39
    衚
    2.38
    Activations Density 0.006%

    No Known Activations