© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31598
    Prev
    Next
    INDEX
    Explanations

    a few

    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_34/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
     banyak
    -1.12
     berbagai
    -0.99
    不同的
    -0.93
     verschillende
    -0.92
     olika
    -0.89
     lebih
    -0.89
    很多
    -0.88
    有多
    -0.88
     مختلف
    -0.88
     muitas
    -0.88
    POSITIVE LOGITS
     few
    5.59
    few
    4.19
     handful
    4.03
    Few
    3.98
     quelques
    3.58
     Few
    3.50
     wenigen
    3.47
     FEW
    3.28
     fewer
    3.16
     wenige
    3.13
    Activations Density 0.209%

    No Known Activations