© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90832
    Prev
    Next
    INDEX
    Explanations

    names of famous individuals

    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
    -1.62
    Также
    -1.59
    🍴
    -1.51
     vaše
    -1.50
     politiet
    -1.49
     SwitchCompat
    -1.41
     offrir
    -1.41
     słucha
    -1.38
    ഛ
    -1.37
    ︕
    -1.36
    POSITIVE LOGITS
     have
    1.96
     
    1.79
     that
    1.59
     one
    1.53
     they
    1.45
     didn
    1.43
     couldn
    1.38
     what
    1.35
     about
    1.34
     don
    1.34
    Activations Density 1.970%

    No Known Activations