© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 358
    Prev
    Next
    INDEX
    Explanations

    narrated by

    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
     αλλά
    -2.86
    ⢧
    -2.75
     namun
    -2.48
     โดย
    -2.44
    ración
    -2.42
     tetapi
    -2.41
     éditoriale
    -2.38
     και
    -2.34
    opardy
    -2.34
     mutta
    -2.33
    POSITIVE LOGITS
    ↵
    3.02
     but
    2.36
    瀦
    2.25
    숱
    2.25
    z
    2.17
     zwart
    2.14
    on
    2.09
    D
    2.06
     indispensable
    2.05
    of
    2.02
    Activations Density 0.002%

    No Known Activations