© 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. 34-GEMMASCOPE-RES-131K
    4. 84794
    Prev
    Next
    INDEX
    Explanations

    java software frameworks

    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_34/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
     because
    -1.55
     with
    -1.49
     even
    -1.48
     all
    -1.45
     on
    -1.45
     out
    -1.44
     any
    -1.36
     or
    -1.36
     from
    -1.31
     within
    -1.30
    POSITIVE LOGITS
     ™
    1.36
     Dinas
    1.23
     ROBERT
    1.20
    atique
    1.20
     verminder
    1.19
     praktische
    1.19
     heridos
    1.17
     betreffende
    1.17
     praktisch
    1.16
     cependant
    1.16
    Activations Density 0.052%

    No Known Activations