© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21399
    Prev
    Next
    INDEX
    Explanations

    exclamations and interjections

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

    The neuron detects emotive interjections or onomatopoeic exclamations (e.g. “ugh,” “gaah,” “eek,” “rrgh”) conveying a strong reaction.

    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
    photographe
    -1.59
     godk
    -1.47
    Tidak
    -1.45
     hırka
    -1.41
     نماز
    -1.37
     dekoratif
    -1.35
     strategis
    -1.35
    írit
    -1.33
     optik
    -1.32
    ﮟ
    -1.30
    POSITIVE LOGITS
     to
    1.53
     by
    1.50
    жнему
    1.41
    を中心
    1.34
    сил
    1.30
     *
    1.27
     The
    1.27
     assist
    1.27
    }
    1.23
    ];
    1.22
    Activations Density 0.013%

    No Known Activations