© 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. 34-GEMMASCOPE-RES-131K
    7. 730
    Prev
    Next
    INDEX
    Explanations

    digital entities and their properties

    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
     perché
    -1.27
     protože
    -1.23
     deoarece
    -1.19
    ǭ
    -1.13
    ᚑ
    -1.11
     dobrze
    -1.10
     adecuadamente
    -1.10
    ものである
    -1.07
     دلیل
    -1.07
     porque
    -1.07
    POSITIVE LOGITS
     without
    3.00
     via
    2.28
     through
    2.09
     with
    2.03
     by
    2.02
     easily
    1.88
     anywhere
    1.77
    without
    1.77
     без
    1.72
     from
    1.71
    Activations Density 0.245%

    No Known Activations