© 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. 34809
    Prev
    Next
    INDEX
    Explanations

    method names

    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
     fonde
    -1.81
     dando
    -1.74
    opie
    -1.74
     AMAZING
    -1.74
    apparently
    -1.73
     interrom
    -1.68
     唯美
    -1.68
     adesivo
    -1.67
     péro
    -1.67
     kompak
    -1.66
    POSITIVE LOGITS
     from
    1.99
     as
    1.94
     or
    1.80
     gives
    1.73
     only
    1.73
     on
    1.73
     give
    1.73
     both
    1.72
     goes
    1.70
     gets
    1.70
    Activations Density 0.020%

    No Known Activations