© 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. 34-GEMMASCOPE-RES-131K
    7. 66259
    Prev
    Next
    INDEX
    Explanations

    jsfiddle.net links

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

    The neuron activates strongly on numeric tokens, especially multi‐digit numbers (i.e. sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     bên
    -0.78
     整
    -0.77
    Fol
    -0.76
    Verification
    -0.75
    solete
    -0.71
    Verify
    -0.71
     verify
    -0.69
     줄
    -0.68
     Verification
    -0.68
    nezeu
    -0.67
    POSITIVE LOGITS
    絹
    0.81
    vcs
    0.73
     lang
    0.68
    tudo
    0.65
     sensory
    0.65
     язы
    0.64
    Corners
    0.63
     Fong
    0.63
    Yin
    0.61
     Vereinigung
    0.61
    Activations Density 0.065%

    No Known Activations