© 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. 34-GEMMASCOPE-RES-131K
    7. 30520
    Prev
    Next
    INDEX
    Explanations

    Ara, Kra, Pra beginnings

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

    The neuron consistently activates on occurrences of the character sequence “ara” (e.g. as the start of words like Ara‐ or ara‐).

    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
    edoria
    -0.93
    nothing
    -0.91
     modifications
    -0.84
    しかも
    -0.81
    -0.80
    digarh
    -0.79
    Otro
    -0.78
    があり
    -0.77
     gemeins
    -0.77
    wage
    -0.77
    POSITIVE LOGITS
    a
    0.91
    ait
    0.90
     régal
    0.89
    iertamente
    0.88
    ToolStripButton
    0.85
    aaaaaaaa
    0.82
     zufrieden
    0.81
     transfé
    0.81
     stycznia
    0.81
     maakte
    0.79
    Activations Density 0.013%

    No Known Activations