© 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. 10-GEMMASCOPE-RES-131K
    4. 70888
    Prev
    Next
    INDEX
    Explanations

    numbers and times

    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
    踯
    -2.11
     étan
    -2.08
    쨩
    -2.03
    Ꮴ
    -1.99
    ſſen
    -1.92
     bascul
    -1.90
     peluche
    -1.89
     délais
    -1.88
     kapture
    -1.86
    ౧
    -1.86
    POSITIVE LOGITS
     with
    2.67
     in
    2.47
     as
    2.39
     from
    2.39
     is
    2.22
     it
    2.16
     or
    1.99
     on
    1.98
     through
    1.88
     for
    1.82
    Activations Density 0.053%

    No Known Activations