© 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. 130915
    Prev
    Next
    INDEX
    Explanations

    tert- followed by a hyphen

    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
     where
    -2.14
     through
    -1.97
     with
    -1.86
     three
    -1.73
     when
    -1.72
     there
    -1.71
     about
    -1.70
     two
    -1.65
     because
    -1.61
     six
    -1.57
    POSITIVE LOGITS
    ni
    1.77
    l
    1.65
     ANOTHER
    1.56
     ſub
    1.49
    GRAPHY
    1.48
    ید
    1.48
     SECOND
    1.45
    ꯷
    1.45
    ized
    1.45
    adomo
    1.43
    Activations Density 0.077%

    No Known Activations