© 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. 10-GEMMASCOPE-RES-131K
    4. 130639
    Prev
    Next
    INDEX
    Explanations

    specific occurrences and states

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

    This neuron detects mentions of “true‐story” or biographical/historical film content (e.g., true stories, biopics, historical dramas).

    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
    ="
    -1.42
     all
    -1.29
     from
    -1.27
    向了
    -1.25
     my
    -1.23
    </em>
    -1.20
    õ
    -1.16
    this
    -1.16
    ias
    -1.14
    !
    -1.14
    POSITIVE LOGITS
     değişik
    1.55
     păr
    1.45
     atacado
    1.39
     eccellente
    1.38
    btnLogin
    1.37
     sviluppo
    1.37
     or
    1.34
    óculos
    1.33
     или
    1.32
    怎麼
    1.32
    Activations Density 0.321%

    No Known Activations