© 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. 114030
    Prev
    Next
    INDEX
    Explanations

    at followed by times

    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
    Negative Logits
     are
    -1.53
     bởi
    -1.53
    The
    -1.45
    乩
    -1.41
    }
    -1.41
    .
    -1.38
     will
    -1.37
    赂
    -1.34
    A
    -1.34
    *
    -1.30
    POSITIVE LOGITS
    筚
    1.67
    禔
    1.61
     an
    1.55
    釭
    1.53
     posting
    1.49
    ⇰
    1.47
    戆
    1.47
    :</
    1.46
     about
    1.42
    别人的
    1.42
    Activations Density 0.071%

    No Known Activations