© 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. 28487
    Prev
    Next
    INDEX
    Explanations

    topic status or context

    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
    6
    -1.32
    7
    -1.14
    some
    -1.14
     изменение
    -1.10
    b
    -1.10
     важно
    -1.09
     africaine
    -1.05
    from
    -1.05
     decenas
    -1.05
    neaux
    -1.05
    POSITIVE LOGITS
     or
    1.46
     which
    1.43
     that
    1.43
     created
    1.38
     existence
    1.28
     their
    1.27
     status
    1.23
     kony
    1.18
    жению
    1.15
     compacto
    1.15
    Activations Density 0.166%

    No Known Activations