© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111472
    Prev
    Next
    INDEX
    Explanations

    is what follows

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

    The neuron fires on occurrences of the copular verb “is” (and, more weakly, other “to be” forms).

    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
     and
    -2.28
    }
    -2.08
     you
    -1.95
     内衣
    -1.84
    ܜ
    -1.82
    際には
    -1.65
     When
    -1.64
     cittadino
    -1.63
     in
    -1.63
     Privacidad
    -1.63
    POSITIVE LOGITS
    н
    2.08
    ”。
    1.89
    </strong>
    1.89
    これで
    1.88
    <bos>
    1.88
     что
    1.74
    磲
    1.74
     שה
    1.72
    ];
    1.69
    ”:
    1.69
    Activations Density 0.087%

    No Known Activations