© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61100
    Prev
    Next
    INDEX
    Explanations

    comparison operators and numerical values

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

    The neuron is primarily triggered by numeric constants (integer literals) in code.

    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
    -2.88
     to
    -2.45
    },
    -2.41
     of
    -2.39
     from
    -2.20
     The
    -2.16
     in
    -2.14
    –
    -2.11
    *
    -2.09
    in
    -2.08
    POSITIVE LOGITS
    šno
    2.34
    Buna
    2.20
    אין
    2.19
     Anexo
    2.16
    Türk
    2.09
    怍
    2.08
     Dijo
    2.08
    钤
    2.03
     größeren
    2.00
    𓆝
    1.99
    Activations Density 0.006%

    No Known Activations