© 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. 9518
    Prev
    Next
    INDEX
    Explanations

    import followed by package

    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
     inmigrantes
    -1.63
    すぎる
    -1.63
     to
    -1.61
     hogares
    -1.53
    ambiental
    -1.49
     ecológica
    -1.47
     rústico
    -1.43
     antiquated
    -1.41
     elaborado
    -1.40
     clunky
    -1.39
    POSITIVE LOGITS
    ísimas
    1.55
    arised
    1.47
    ess
    1.46
    ges
    1.38
     produse
    1.38
    THING
    1.38
    ſche
    1.38
    OOOO
    1.35
     "..\..\
    1.34
     infine
    1.34
    Activations Density 0.008%

    No Known Activations