© 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. 22-GEMMASCOPE-RES-131K
    7. 95806
    Prev
    Next
    INDEX
    Explanations

    version and data

    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_22/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
    酲
    -2.02
    を
    -1.96
    〜。
    -1.95
     onCreateView
    -1.95
    ～。
    -1.94
    があります
    -1.92
     onPostExecute
    -1.91
     in
    -1.90
    。　　
    -1.86
    ghouse
    -1.86
    POSITIVE LOGITS
     and
    3.00
    為に
    2.42
    感じで
    2.39
    ときの
    2.30
    ところに
    2.25
    感じが
    2.20
    割と
    2.13
    に行って
    2.11
    すっ
    2.08
    きち
    2.02
    Activations Density 0.005%

    No Known Activations