© 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. 40192
    Prev
    Next
    INDEX
    Explanations

    actions and their consequences

    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
    either
    -1.47
     either
    -1.40
     indivíduos
    -1.23
    を行い
    -1.22
     entweder
    -1.21
    This
    -1.21
    だけではなく
    -1.19
    啐
    -1.17
     enten
    -1.14
     .........
    -1.13
    POSITIVE LOGITS
     after
    2.11
     in
    1.97
    だが
    1.59
     on
    1.57
     with
    1.54
     после
    1.50
     despite
    1.49
     six
    1.45
    後は
    1.41
     após
    1.41
    Activations Density 0.118%

    No Known Activations