© 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. 48529
    Prev
    Next
    INDEX
    Explanations

    text labels from code and research

    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
    orescent
    -0.82
    PageState
    -0.77
    连续
    -0.72
    "]).
    -0.70
    $-$
    -0.70
     myriad
    -0.68
     turi
    -0.68
    propTypes
    -0.67
    Convenient
    -0.66
     piet
    -0.66
    POSITIVE LOGITS
     Zamb
    0.82
     rhythms
    0.81
     Partai
    0.77
     Ulu
    0.77
     nech
    0.76
    ardı
    0.75
     немає
    0.75
     bakom
    0.74
    Farmer
    0.74
    主力
    0.74
    Activations Density 0.003%

    No Known Activations