© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116490
    Prev
    Next
    INDEX
    Explanations

    technical dates and software

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

    The main thing this neuron does is detect numeric tokens and punctuation in numeric sequences (e.g. digits in titles, model numbers, years).

    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
     condenado
    -0.69
     beleza
    -0.68
    junct
    -0.68
     Reflex
    -0.67
     commuting
    -0.66
     仔
    -0.66
    mande
    -0.66
    dox
    -0.65
    ým
    -0.65
     Folding
    -0.65
    POSITIVE LOGITS
     clutch
    0.82
     Boost
    0.81
    eurovision
    0.79
    детская
    0.77
     dropper
    0.77
    tieg
    0.76
     Trail
    0.75
     suspension
    0.75
    bandcamp
    0.74
     Hydraulic
    0.74
    Activations Density 0.007%

    No Known Activations