© 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. 80021
    Prev
    Next
    INDEX
    Explanations

    national bestseller

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

    The neuron fires strongly on semantically informative “content” tokens (not common function words)—for example, key nouns, verbs, and other topic‐bearing words.

    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
     Pourquoi
    -1.21
     maler
    -1.12
     familien
    -1.09
     Otros
    -1.07
    STON
    -1.06
     septembre
    -1.04
     Jika
    -1.01
    जी
    -1.00
     Outros
    -0.99
     Warum
    -0.98
    POSITIVE LOGITS
    .”
    1.20
    ).
    1.15
    }$.
    1.09
     ہے۔
    1.06
     ہیں۔
    1.00
     just
    0.99
    ”.
    0.99
     berlina
    0.93
    .")
    0.91
    </h2>
    0.91
    Activations Density 0.034%

    No Known Activations