© 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. 68211
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    ícias
    -1.24
     Fähigkeit
    -1.22
    },{
    -1.20
    ducers
    -1.19
    Ꮴ
    -1.14
    ∖
    -1.13
     diren
    -1.11
     loci
    -1.10
    hoku
    -1.10
    Externé
    -1.09
    POSITIVE LOGITS
     ולה
    1.20
     be
    1.15
     in
    1.15
     навіть
    1.07
     There
    1.05
    garmin
    1.00
     of
    0.98
    瓶
    0.96
    8
    0.96
    </h2>
    0.96
    Activations Density 0.042%

    No Known Activations