© 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. 10-GEMMASCOPE-RES-131K
    7. 11299
    Prev
    Next
    INDEX
    Explanations

    single unit or page

    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_10/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
    four
    -1.40
     ранее
    -1.36
    哄
    -1.32
     všet
    -1.30
    REQU
    -1.28
     områ
    -1.27
     alterar
    -1.27
     Iglesias
    -1.26
     гле
    -1.25
     and
    -1.23
    POSITIVE LOGITS
     such
    1.82
     these
    1.68
     this
    1.55
     for
    1.53
     the
    1.46
     either
    1.41
     those
    1.39
     causing
    1.32
     breiten
    1.31
     including
    1.29
    Activations Density 0.065%

    No Known Activations