© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72634
    Prev
    Next
    INDEX
    Explanations

    US dollars

    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
     in
    -1.77
     at
    -1.63
     S
    -1.55
     as
    -1.55
     with
    -1.49
     other
    -1.47
     L
    -1.46
     D
    -1.45
     T
    -1.44
     on
    -1.41
    POSITIVE LOGITS
    麃
    1.50
     jednod
    1.47
    KURZ
    1.45
     Conſ
    1.43
     verhind
    1.42
     anunció
    1.40
     uſe
    1.38
     célè
    1.37
     Diſ
    1.36
     geene
    1.36
    Activations Density 0.138%

    No Known Activations