© 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. 10-GEMMASCOPE-RES-131K
    7. 19129
    Prev
    Next
    INDEX
    Explanations

    similarity and comparison

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of the word “alike” (used in comparative contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     is
    -3.61
     he
    -2.72
     ”
    -2.47
     t
    -2.44
     We
    -2.41
    ’
    -2.33
     ‘
    -2.28
     to
    -2.11
    <b>
    -2.09
     n
    -2.09
    POSITIVE LOGITS
     unſ
    2.41
     cristo
    2.31
     putri
    2.27
     milliards
    2.25
    垍
    2.20
    킁
    2.19
    ؛
    2.17
     yako
    2.14
    dzić
    2.13
    
    2.11
    Activations Density 0.002%

    No Known Activations