© 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. 60783
    Prev
    Next
    INDEX
    Explanations

    imaging boutique

    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
     these
    -1.80
     what
    -1.63
     such
    -1.42
     oppervlak
    -1.27
     those
    -1.27
     circunstancia
    -1.23
    ्रेस
    -1.23
    )");
    -1.20
    imbang
    -1.18
     the
    -1.17
    POSITIVE LOGITS
    They
    1.84
    1.55
    begin
    1.43
    が
    1.42
    を
    1.41
     "
    1.38
    0
    1.36
    em
    1.35
    或者
    1.34
    ють
    1.34
    Activations Density 0.130%
    No Known Activations