© 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. 70540
    Prev
    Next
    INDEX
    Explanations

    possibly, can, help

    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
     剤
    -2.89
    缡
    -2.83
    魨
    -2.81
    ⩴
    -2.67
    ﺐ
    -2.50
    </h3>
    -2.48
    桄
    -2.42
     därför
    -2.39
    䡲
    -2.39
    쫀
    -2.38
    POSITIVE LOGITS
    </b>
    3.08
    </td>
    2.72
    ra
    2.34
    s
    2.27
    [
    2.25
    <b>
    2.23
    am
    2.20
    ie
    2.17
    (
    2.14
     полного
    2.13
    Activations Density 0.001%

    No Known Activations