© 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. 23902
    Prev
    Next
    INDEX
    Explanations

    naive individuals and subjects

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

    The neuron fires on occurrences of the word “naive.”

    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
     що
    -2.45
    </h3>
    -2.44
    </strong>
    -2.38
    ());
    -2.17
     say
    -2.13
    ра
    -2.13
    ):
    -2.13
    .},
    -2.11
    <td>
    -2.09
    ’
    -2.09
    POSITIVE LOGITS
     initWithFrame
    2.33
     bemer
    2.06
     IndexPath
    1.98
    ㉗
    1.95
    where
    1.93
    changers
    1.92
    ᥫ
    1.88
     demek
    1.88
     sami
    1.84
    蒾
    1.84
    Activations Density 0.002%

    No Known Activations