© 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. 59237
    Prev
    Next
    INDEX
    Explanations

    number two

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

    The neuron selectively activates on the spelled-out numeral “two.”

    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
    )
    -2.03
    s
    -1.94
    ly
    -1.91
    po
    -1.88
    le
    -1.83
    ra
    -1.76
    4
    -1.76
    ar
    -1.74
    pe
    -1.70
    ca
    -1.70
    POSITIVE LOGITS
     These
    1.90
     with
    1.88
    })$,
    1.77
    𝔃
    1.75
     மற்றும்
    1.71
     from
    1.69
     нього
    1.68
     και
    1.67
    ’:
    1.64
    西哥
    1.64
    Activations Density 0.082%

    No Known Activations