© 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. 109513
    Prev
    Next
    INDEX
    Explanations

    editors and editions

    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
     and
    -2.48
     to
    -2.05
     for
    -1.75
     this
    -1.66
     which
    -1.65
     whose
    -1.48
     because
    -1.41
     of
    -1.38
     on
    -1.38
     or
    -1.35
    POSITIVE LOGITS
     prét
    1.47
     refroid
    1.42
     réessayer
    1.38
     manquer
    1.37
     incess
    1.35
    issait
    1.30
     rafra
    1.28
     ralenti
    1.27
     indio
    1.27
     ressort
    1.27
    Activations Density 0.010%

    No Known Activations