© 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. 104472
    Prev
    Next
    INDEX
    Explanations

    you and your

    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
    んでも
    -1.36
    ־
    -1.13
    げた
    -1.12
     edy
    -1.11
    ptăm
    -1.09
    舛
    -1.07
     nien
    -1.06
     tych
    -1.04
    —————
    -1.03
    -),
    -1.02
    POSITIVE LOGITS
     you
    2.61
     your
    1.76
    Although
    1.52
    You
    1.51
    When
    1.45
    Another
    1.44
    According
    1.38
    如果你
    1.37
    你要
    1.30
    There
    1.27
    Activations Density 0.004%

    No Known Activations