© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13890
    Prev
    Next
    INDEX
    Explanations

    RSV

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

    the redirection operator (>>) in code or text formatting.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of the “>>” token (double greater-than symbols).

    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
    0
    -3.45
    *
    -3.00
    1
    -2.69
    Two
    -2.50
    Using
    -2.28
    When
    -2.25
     “
    -2.20
    Not
    -2.16
    |
    -2.14
    What
    -2.09
    POSITIVE LOGITS
    籏
    3.56
    s
    3.33
    
    2.83
    ㉕
    2.38
    嫆
    2.33
     donnent
    2.28
    了
    2.27
    茀
    2.25
    OUTUBE
    2.25
    釤
    2.23
    Activations Density 0.001%

    No Known Activations