© 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. 65051
    Prev
    Next
    INDEX
    Explanations

    bracketed names and references

    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
     if
    -1.60
    1
    -1.59
    When
    -1.59
     or
    -1.58
    子さん
    -1.53
     when
    -1.52
    ちなみに
    -1.49
    sakura
    -1.41
    In
    -1.38
    龶
    -1.38
    POSITIVE LOGITS
    </h2>
    2.14
    镡
    1.60
    ㇼ
    1.60
    .},
    1.59
     affirms
    1.59
    ⁛
    1.58
    </em>
    1.56
    ;</
    1.54
    嫆
    1.54
    憷
    1.52
    Activations Density 0.006%

    No Known Activations