© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75240
    Prev
    Next
    INDEX
    Explanations

    ends processes or loops

    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
    と思われます
    -1.24
     paixão
    -1.13
    bbt
    -1.13
    uncias
    -1.12
     decidedly
    -1.11
     náš
    -1.10
    簠
    -1.10
     suceso
    -1.09
    なるべく
    -1.09
     účast
    -1.09
    POSITIVE LOGITS
     after
    1.28
    After
    1.22
    !
    1.08
     sooooo
    1.05
    There
    1.03
     battling
    1.02
     probably
    0.99
    ,
    0.97
    ');
    0.96
    It
    0.94
    Activations Density 0.001%

    No Known Activations