© 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. 19554
    Prev
    Next
    INDEX
    Explanations

    inc

    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
    on
    -2.48
    er
    -2.41
    0
    -2.41
    と
    -2.41
    偏偏
    -2.36
    ーーーー
    -2.31
    を
    -2.17
    g
    -2.16
    孩子的
    -2.14
    *
    -2.14
    POSITIVE LOGITS
    ’:
    2.47
    鵟
    2.41
    はこんな感じ
    2.16
    颡
    2.14
     of
    2.13
    </h3>
    2.11
    饪
    2.06
    ๐
    2.06
    </strong>
    2.05
    也将
    2.05
    Activations Density 0.004%

    No Known Activations