© 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. 40942
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

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

    The neuron fires on numeric literal tokens (i.e. numbers appearing in the text).

    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
    with
    -2.91
    ing
    -2.89
    Like
    -2.83
    Only
    -2.75
    With
    -2.70
    For
    -2.67
    Other
    -2.67
    One
    -2.66
    After
    -2.64
    I
    -2.59
    POSITIVE LOGITS
    </strong>
    2.84
     they
    2.78
    ⃤
    2.36
    *);
    2.25
     was
    2.22
    手腕
    2.16
    钐
    2.16
    はこの
    2.14
    でした
    2.13
    _);
    2.13
    Activations Density 0.008%

    No Known Activations