© 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. 104728
    Prev
    Next
    INDEX
    Explanations

    flag representations or attributes

    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
    7
    -2.45
    </h2>
    -2.44
     However
    -2.25
     –
    -2.19
     $
    -2.11
    蹿
    -2.09
     ).
    -2.06
         
    -2.02
    h
    -1.98
     else
    -1.97
    POSITIVE LOGITS
    ꒥
    2.55
    ዡ
    2.44
     内衣
    2.44
     帅气
    2.39
     ſta
    2.36
    druk
    2.31
     voorbere
    2.30
     ſaid
    2.28
     faſt
    2.28
    iç
    2.25
    Activations Density 0.007%

    No Known Activations