© 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. 114000
    Prev
    Next
    INDEX
    Explanations

    individuals and groups

    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
     immense
    -1.65
     amazing
    -1.53
     sorriso
    -1.41
    tent
    -1.40
     REALLY
    -1.40
    Nope
    -1.40
     amazingly
    -1.40
    Understand
    -1.40
     hahaha
    -1.40
    yeah
    -1.39
    POSITIVE LOGITS
     makes
    1.71
    彼らの
    1.64
     For
    1.55
     there
    1.53
     їх
    1.51
     but
    1.47
    ﾍ
    1.45
     seeks
    1.45
     creates
    1.44
     an
    1.42
    Activations Density 0.018%

    No Known Activations