© 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. 75322
    Prev
    Next
    INDEX
    Explanations

    medical marijuana

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

    The neuron detects question and answer dialogue patterns in text, particularly in interview formats.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron highlights the key topic words and main content-bearing verbs that define what each segment is about.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Since
    -1.49
     Since
    -1.44
     disconcer
    -1.39
     While
    -1.38
    While
    -1.37
     unequivocally
    -1.33
    انظر
    -1.31
     noteworthy
    -1.30
     will
    -1.30
    حوال
    -1.29
    POSITIVE LOGITS
     you
    1.66
     kinda
    1.37
     your
    1.37
    maybe
    1.34
     étions
    1.33
     []:
    1.33
     kind
    1.29
     Inſ
    1.25
    generally
    1.23
     [
    1.21
    Activations Density 0.001%

    No Known Activations