© 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. 113533
    Prev
    Next
    INDEX
    Explanations

    for loop

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

    colons that appear after numeric indices in programming code, particularly in range or loop syntax.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is sensitive to numeric tokens (literal numbers) in the text.

    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
    E
    -2.08
    {
    -1.97
    </strong>
    -1.92
     {
    -1.89
    u
    -1.86
    1
    -1.86
    .
    -1.84
    r
    -1.84
    me
    -1.83
    o
    -1.80
    POSITIVE LOGITS
     navide
    2.31
     torba
    2.06
    rozum
    1.95
    Bety
    1.86
     素描
    1.85
     malé
    1.81
     우리
    1.80
     indiví
    1.79
    Metode
    1.78
     eşofman
    1.78
    Activations Density 0.003%

    No Known Activations