© 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. 110840
    Prev
    Next
    INDEX
    Explanations

    phone calls

    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
     of
    -2.22
    m
    -2.20
    k
    -2.08
    j
    -1.83
    f
    -1.79
    as
    -1.78
    w
    -1.77
    ag
    -1.63
    and
    -1.60
    ”,
    -1.56
    POSITIVE LOGITS
    噥
    1.86
     two
    1.82
    zmm
    1.72
    旆
    1.59
    mohon
    1.59
    pulseira
    1.58
     tidligere
    1.57
    --.
    1.55
    rmk
    1.55
     две
    1.54
    Activations Density 0.038%

    No Known Activations