© 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. 9415
    Prev
    Next
    INDEX
    Explanations

    calling this new land home

    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
    その
    -1.63
    って思
    -1.60
    もちろん
    -1.57
    ～。
    -1.56
    (´
    -1.55
    つまり
    -1.54
    轍
    -1.53
     (
    -1.50
    靄
    -1.49
    などなど
    -1.48
    POSITIVE LOGITS
    為に
    2.41
    様な
    2.19
    際に
    2.11
    すっ
    2.11
    ほら
    2.11
    際には
    2.08
    凄く
    1.95
    ようになって
    1.88
    さき
    1.86
    づけ
    1.85
    Activations Density 0.067%

    No Known Activations