© 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. 11013
    Prev
    Next
    INDEX
    Explanations

    operational sites

    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
     different
    -1.66
     including
    -1.59
     many
    -1.45
     anzunehmen
    -1.40
     like
    -1.38
     available
    -1.38
     appropriate
    -1.30
     typical
    -1.30
     for
    -1.29
     specific
    -1.29
    POSITIVE LOGITS
     Inſ
    1.30
     ronde
    1.30
    ása
    1.28
     Türkiye
    1.27
     favoriser
    1.23
    yea
    1.23
     problèmes
    1.19
     Italy
    1.18
    Bry
    1.17
     THOSE
    1.17
    Activations Density 0.053%

    No Known Activations