© 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. 59271
    Prev
    Next
    INDEX
    Explanations

    units of length

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

    The neuron fires on numeric length measurements expressed in millimeters.

    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
    使った
    -2.03
    の前に
    -2.02
    .«
    -2.00
    vlá
    -1.98
    
    -1.88
     splendid
    -1.84
     stalwart
    -1.83
     
    -1.81
     steeped
    -1.81
     glaub
    -1.81
    POSITIVE LOGITS
    for
    2.38
    with
    2.31
    and
    2.30
    ных
    2.22
    0
    2.20
     для
    2.13
    of
    2.06
    from
    2.00
    viembre
    2.00
    к
    1.98
    Activations Density 0.000%

    No Known Activations