© 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. 20671
    Prev
    Next
    INDEX
    Explanations

    dialog and code snippets

    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
     will
    -2.14
    1
    -1.51
    </b>
    -1.51
     панель
    -1.47
    What
    -1.44
    How
    -1.41
     and
    -1.40
    使得
    -1.39
    to
    -1.36
     would
    -1.34
    POSITIVE LOGITS
    🔚
    1.34
     respectivos
    1.34
    fordable
    1.30
    всегда
    1.30
     restos
    1.29
    跺
    1.27
    噠
    1.27
     única
    1.27
     丝
    1.27
    OGLYPH
    1.27
    Activations Density 0.012%

    No Known Activations