© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105608
    Prev
    Next
    INDEX
    Explanations

    launch

    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
    </h3>
    -3.38
     -
    -2.91
    </strong>
    -2.69
     are
    -2.58
     す
    -2.42
     prompting
    -2.27
    /
    -2.23
     To
    -2.19
     situés
    -2.19
     この
    -2.17
    POSITIVE LOGITS
    蹀
    2.84
    笮
    2.61
    鲽
    2.58
    퐼
    2.55
    毐
    2.52
    </b>
    2.45
    锖
    2.42
     plupart
    2.41
     ハロウィン
    2.34
    茀
    2.33
    Activations Density 0.010%

    No Known Activations