© 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. 65110
    Prev
    Next
    INDEX
    Explanations

    teacher roles and contexts

    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
     '
    -2.98
    ’
    -2.95
    ,'
    -2.77
     –
    -2.53
    𖣘
    -2.25
     drenched
    -2.19
     pinnacle
    -2.17
    了你
    -2.17
    ously
    -2.13
    摄影
    -2.13
    POSITIVE LOGITS
    </td>
    2.95
     メニュー
    2.88
    狆
    2.70
    蔸
    2.56
    憮
    2.52
     ▸
    2.52
     titolata
    2.48
    觔
    2.47
     eif
    2.42
     ★★★★
    2.42
    Activations Density 0.010%

    No Known Activations