© 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. 79790
    Prev
    Next
    INDEX
    Explanations

    registered trademark symbol and brands

    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
     and
    -1.31
    }\
    -1.31
     denne
    -1.30
    九年
    -1.21
     guste
    -1.16
     this
    -1.16
    招生
    -1.16
     they
    -1.14
     كو
    -1.14
    źni
    -1.13
    POSITIVE LOGITS
    ®
    2.55
    ®,
    1.95
    ®.
    1.69
     ®
    1.67
    ®-
    1.57
    ™
    1.46
    circledR
    1.21
    がある
    1.21
     všem
    1.10
     wrze
    1.06
    Activations Density 0.062%

    No Known Activations