© 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. 79756
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and probability sequences

    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
    नलोड
    -1.44
     GOOD
    -1.41
     TWO
    -1.40
    توضیحات
    -1.31
     великолеп
    -1.30
    Ikke
    -1.30
    tya
    -1.28
    OTTEN
    -1.27
    Generally
    -1.27
     seres
    -1.26
    POSITIVE LOGITS
     also
    1.59
    就可以了
    1.44
     bijvoorbeeld
    1.37
    ?
    1.34
    の説明
    1.31
     navíc
    1.27
     therefore
    1.27
    </b>
    1.27
     jouw
    1.26
    就行了
    1.26
    Activations Density 0.034%

    No Known Activations