© 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. 40968
    Prev
    Next
    INDEX
    Explanations

    humanitarian aid and relief

    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
     or
    -1.54
     your
    -1.46
     about
    -1.41
     if
    -1.30
     that
    -1.25
     intricacies
    -1.23
     one
    -1.19
     revital
    -1.16
     الن
    -1.13
     tentang
    -1.13
    POSITIVE LOGITS
    垰
    1.38
    出了一
    1.37
    both
    1.28
     ludicrous
    1.27
     spearheaded
    1.27
    のおかげ
    1.25
     ausgewählt
    1.25
     tremendous
    1.24
     dergleichen
    1.24
    during
    1.23
    Activations Density 0.077%

    No Known Activations