© 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. 27192
    Prev
    Next
    INDEX
    Explanations

    content sourced from

    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
    ڧ
    -1.34
    柃
    -1.27
     keV
    -1.20
    
    -1.19
     ultimi
    -1.17
    atá
    -1.11
     recompensa
    -1.10
    еремо
    -1.10
    Geografie
    -1.08
    varet
    -1.08
    POSITIVE LOGITS
     from
    5.09
     từ
    1.83
     از
    1.81
    from
    1.80
     kutoka
    1.79
    จาก
    1.64
     From
    1.41
     daripada
    1.39
     από
    1.38
     of
    1.38
    Activations Density 0.043%

    No Known Activations