© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26007
    Prev
    Next
    INDEX
    Explanations

    recommendation quotes

    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
    越來
    -1.05
    いずれ
    -1.02
    回憶
    -0.97
    漲
    -0.96
     items
    -0.96
     Ministero
    -0.96
     other
    -0.96
     some
    -0.96
     用于
    -0.95
     various
    -0.94
    POSITIVE LOGITS
    Rating
    1.29
    dö
    1.23
     Rating
    1.21
     rating
    1.19
    RATING
    1.17
     Verdict
    1.14
    Verdict
    1.13
    推荐
    1.13
    Recommendation
    1.13
     recommend
    1.09
    Activations Density 0.009%

    No Known Activations