© 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. 10-GEMMASCOPE-RES-131K
    7. 44714
    Prev
    Next
    INDEX
    Explanations

    importance, necessity, and difficulty

    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
    still
    -1.77
     still
    -1.72
     currently
    -1.67
     अभी
    -1.65
     now
    -1.65
    currently
    -1.55
     then
    -1.53
     actuellement
    -1.52
     этом
    -1.34
    这是一
    -1.34
    POSITIVE LOGITS
     for
    2.17
     in
    1.54
     with
    1.42
     if
    1.41
     when
    1.38
    ということで
    1.35
    됩니다
    1.29
     özellikle
    1.26
    čů
    1.25
     after
    1.24
    Activations Density 0.063%

    No Known Activations