© 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. 131036
    Prev
    Next
    INDEX
    Explanations

    FILED U.S. COURT OF APPEALS

    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
    Также
    -1.46
    </u>
    -1.45
    另一個
    -1.45
     sozialen
    -1.41
    Also
    -1.39
    不僅
    -1.35
    همچنین
    -1.30
     jungen
    -1.30
     réputation
    -1.30
    >
    -1.29
    POSITIVE LOGITS
    .
    1.41
    只是一
    1.39
    </h2>
    1.26
    edì
    1.26
     alguns
    1.24
     who
    1.20
     we
    1.19
    haustible
    1.18
     jejich
    1.17
     cette
    1.16
    Activations Density 0.079%

    No Known Activations