© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127613
    Prev
    Next
    INDEX
    Explanations

    vintage item descriptors

    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
    犼
    -2.72
    詎
    -2.70
    檮
    -2.69
     ビキニ
    -2.56
    拊
    -2.52
    珰
    -2.39
    肏
    -2.38
    馓
    -2.36
    塍
    -2.33
    慊
    -2.30
    POSITIVE LOGITS
    i
    3.08
    However
    2.84
    While
    2.70
    —
    2.66
    Q
    2.47
    It
    2.45
    ↵
    2.41
    This
    2.38
    If
    2.33
     These
    2.33
    Activations Density 0.002%

    No Known Activations