© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112020
    Prev
    Next
    INDEX
    Explanations

    form of

    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
     xícara
    -2.13
     Anſ
    -2.02
    口气
    -2.02
     októ
    -1.90
     totalité
    -1.90
    が起こ
    -1.84
     unicórnio
    -1.79
    齜
    -1.78
     llena
    -1.77
    のいい
    -1.77
    POSITIVE LOGITS
    ”
    2.78
    </h3>
    2.52
    <strong>
    2.39
    m
    2.38
    ts
    2.36
    t
    2.30
    其
    2.22
    <em>
    2.20
    on
    2.14
    “
    2.14
    Activations Density 0.010%

    No Known Activations