© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11508
    Prev
    Next
    INDEX
    Explanations

    events happening after something

    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
     may
    -1.42
     if
    -1.36
     should
    -1.25
     однако
    -1.17
     could
    -1.16
     until
    -1.15
     Probably
    -1.13
     at
    -1.11
     can
    -1.10
     truly
    -1.09
    POSITIVE LOGITS
     recent
    1.41
    ַּ
    1.30
     receber
    1.30
    ִּ
    1.26
     descobri
    1.23
     recently
    1.21
     prática
    1.17
    ֶּ
    1.17
     yesterday
    1.16
     работает
    1.16
    Activations Density 0.060%

    No Known Activations