© 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. 22-GEMMASCOPE-RES-131K
    4. 95523
    Prev
    Next
    INDEX
    Explanations

    medical marijuana to hunting dogs

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

    words related to industrial, professional, and military sectors or contexts.

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

    The neuron fires on high-level domain or section headings—single words that name the field or topic (e.g. “Medical,” “Industrial,” “Military,” “Enterprise,” etc.).

    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
    Witaj
    -1.19
    larna
    -1.18
    odotus
    -1.17
    ḇ
    -1.13
    Dział
    -1.13
    setArguments
    -1.12
     loob
    -1.08
    lji
    -1.06
    
    -1.06
    Dimensioni
    -1.05
    POSITIVE LOGITS
    y
    1.16
    :
    1.15
    r
    1.14
    P
    1.14
     from
    1.13
     in
    1.12
    a
    1.10
     purpose
    1.06
    용
    1.01
    in
    0.98
    Activations Density 0.313%

    No Known Activations