© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104535
    Prev
    Next
    INDEX
    Explanations

    Scripture formatting and questions

    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
     of
    -1.88
     on
    -1.48
     to
    -1.48
     also
    -1.48
     However
    -1.45
     by
    -1.33
    кож
    -1.30
     According
    -1.30
    endforeach
    -1.26
     polícia
    -1.26
    POSITIVE LOGITS
     vlasy
    1.39
    problema
    1.36
    鉏
    1.33
    ficha
    1.31
    眺め
    1.30
    充满了
    1.30
    oczes
    1.27
     oscu
    1.26
    packung
    1.25
     adonan
    1.25
    Activations Density 0.003%

    No Known Activations