© 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. 22506
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code snippets

    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
     and
    -2.06
     by
    -1.69
     even
    -1.62
     just
    -1.60
     both
    -1.58
     still
    -1.48
     with
    -1.44
     this
    -1.40
    🕚
    -1.36
     but
    -1.32
    POSITIVE LOGITS
    idk
    1.51
     erheb
    1.46
     isolamento
    1.45
    Otra
    1.38
    ﮦ
    1.36
     bizarre
    1.34
    ことなく
    1.34
     kinda
    1.34
    がなく
    1.34
     andare
    1.34
    Activations Density 0.096%

    No Known Activations