© 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. 129150
    Prev
    Next
    INDEX
    Explanations

    give or provide

    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
    6
    -1.87
    id
    -1.79
    2
    -1.70
    am
    -1.55
    运算
    -1.53
     производстве
    -1.52
     hadi
    -1.51
    i
    -1.45
    地在
    -1.43
    3
    -1.43
    POSITIVE LOGITS
     where
    2.17
     ocurrió
    1.63
     just
    1.63
     when
    1.59
     more
    1.55
     outras
    1.51
     otras
    1.50
     Maybe
    1.48
     something
    1.47
     a
    1.42
    Activations Density 0.005%

    No Known Activations