© 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. 22-GEMMASCOPE-RES-131K
    7. 98473
    Prev
    Next
    INDEX
    Explanations

    class names

    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
    umers
    -1.11
    ющими
    -1.09
     المزيد
    -1.08
    Trichlor
    -1.07
    sandy
    -1.06
     feveral
    -1.06
     kolon
    -1.05
     kosme
    -1.05
     Sekret
    -1.02
    yit
    -1.02
    POSITIVE LOGITS
     who
    1.34
     azonban
    1.18
     озе
    1.13
    _
    1.12
     jedoch
    1.02
     That
    1.02
    さんも
    1.00
    ٦
    1.00
    有
    1.00
    بله
    0.98
    Activations Density 0.027%

    No Known Activations