© 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. 37802
    Prev
    Next
    INDEX
    Explanations

    progress dialog and stages

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

    The neuron responds to multi‐digit numerical tokens (especially sequences of three or more 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
     may
    -1.01
    say
    -0.91
     say
    -0.89
     might
    -0.87
    omers
    -0.84
     says
    -0.82
    >",
    -0.81
    !
    -0.79
    》，
    -0.79
    )，
    -0.77
    POSITIVE LOGITS
     $
    1.59
    riges
    0.85
     глазах
    0.83
    ,$
    0.82
     Loved
    0.82
     ProgressDialog
    0.81
    々の
    0.80
    мино
    0.80
     doel
    0.80
    Honorary
    0.79
    Activations Density 0.036%

    No Known Activations