© 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. 22-GEMMASCOPE-RES-131K
    7. 27384
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, or common words

    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_22/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
    Ops
    -0.94
    xtype
    -0.93
     Australian
    -0.90
    AHUL
    -0.89
    зме
    -0.89
    勐
    -0.89
    bitmap
    -0.88
    ButtonGroup
    -0.87
     Coaster
    -0.86
     triliun
    -0.85
    POSITIVE LOGITS
     będzie
    1.09
     who
    1.08
     procesador
    1.03
    の詳細
    1.02
     convertido
    1.00
     conectado
    0.98
    已經
    0.97
     digno
    0.96
    appear
    0.96
     û
    0.96
    Activations Density 0.004%

    No Known Activations