© 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. 40346
    Prev
    Next
    INDEX
    Explanations

    not require or optional

    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
     некоторых
    -0.98
    믐
    -0.97
    hiro
    -0.96
    这让
    -0.95
    кус
    -0.94
    Notae
    -0.93
     rightful
    -0.91
    ではなく
    -0.90
     zamiast
    -0.89
    ̀
    -0.89
    POSITIVE LOGITS
     anymore
    2.03
     any
    1.85
     nor
    1.56
     or
    1.56
     because
    1.42
     unless
    1.42
     necessarily
    1.40
     אלא
    1.30
     except
    1.26
     anything
    1.22
    Activations Density 0.055%

    No Known Activations