© 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. 59621
    Prev
    Next
    INDEX
    Explanations

    Bahraini, Baham, Behçet’s, Bahadur, Bach

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

    The neuron is looking for the character sequence “b-a-h” (or “b-e-h”) in tokens.

    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
    bereitung
    -0.77
    SUC
    -0.73
     finca
    -0.73
     defectos
    -0.73
    ثیر
    -0.73
     Stereo
    -0.73
    Stereo
    -0.73
    createForm
    -0.71
    Usb
    -0.71
    手間
    -0.69
    POSITIVE LOGITS
     uważ
    0.85
     bah
    0.83
    bah
    0.79
     jeżeli
    0.78
     nhựa
    0.78
     docile
    0.74
    剥
    0.73
     Anyway
    0.73
     auditor
    0.72
     incursion
    0.71
    Activations Density 0.008%

    No Known Activations