© 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. 39302
    Prev
    Next
    INDEX
    Explanations

    uch/och/rch endings

    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
     camiset
    -2.78
    鸲
    -2.72
    蕺
    -2.66
    ’:
    -2.63
    翾
    -2.58
    珢
    -2.53
     ſie
    -2.53
    焿
    -2.48
    鈊
    -2.41
     放題
    -2.38
    POSITIVE LOGITS
    s
    4.22
    </td>
    3.66
    5
    3.53
    3
    3.30
    '
    3.19
    6
    2.91
    4
    2.84
    7
    2.78
    2
    2.77
    </b>
    2.64
    Activations Density 0.250%

    No Known Activations