© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60347
    Prev
    Next
    INDEX
    Explanations

    humorous texts stories view twinkle Silaran Prin Florian

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

    This neuron activates on occurrences of the substring “humor” (as in “humorous”).

    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
    </h4>
    -3.78
     ");
    -2.97
     */
    -2.97
     }
    -2.94
    ↵↵
    -2.92
    </sup>
    -2.77
    8
    -2.73
    -
    -2.72
    2
    -2.70
     I
    -2.47
    POSITIVE LOGITS
    </i>
    4.06
     laajenta
    2.50
    鱟
    2.45
    佮
    2.36
    </h3>
    2.22
     ドア
    2.20
     gets
    2.19
     increases
    2.13
    tadır
    2.13
     explicitly
    2.11
    Activations Density 0.004%

    No Known Activations