© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    why followed by a subject

    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
    cjon
    -1.35
    (=)
    -1.29
    metik
    -1.24
     metus
    -1.24
    espół
    -1.21
    jmu
    -1.20
    ***/
    -1.19
     pandemia
    -1.17
    przed
    -1.17
     {
    -1.16
    POSITIVE LOGITS
     A
    1.27
    '
    1.27
     |
    1.25
    ,
    1.21
    It
    1.16
    )}+
    1.14
    Do
    1.13
    全都
    1.13
     '
    1.13
    The
    1.13
    Activations Density 0.001%

    No Known Activations