© 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. 112268
    Prev
    Next
    INDEX
    Explanations

    found / find

    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
     However
    -1.68
     December
    -1.60
     cualquier
    -1.59
     vermutlich
    -1.55
     When
    -1.55
     Furthermore
    -1.52
     Bemerkungen
    -1.47
    焄
    -1.46
     September
    -1.45
     aktuellen
    -1.43
    POSITIVE LOGITS
     jardins
    1.43
     stijl
    1.31
     Komis
    1.30
    »,
    1.29
     journaux
    1.28
     milliers
    1.26
    Myself
    1.25
     victoires
    1.25
    arise
    1.25
     poches
    1.23
    Activations Density 0.035%

    No Known Activations