© 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. 3662
    Prev
    Next
    INDEX
    Explanations

    program identifiers or keywords

    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
     both
    -1.59
     two
    -1.57
     v
    -1.52
     "
    -1.50
     by
    -1.49
     or
    -1.44
    V
    -1.41
    <sup>
    -1.41
     -
    -1.40
     is
    -1.39
    POSITIVE LOGITS
    ఙ
    1.48
     lópez
    1.48
     utilisées
    1.46
    毟
    1.45
     cihaz
    1.45
     the
    1.44
     dieß
    1.41
    kệ
    1.40
     pattes
    1.40
    használ
    1.40
    Activations Density 0.021%

    No Known Activations