© 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. 49449
    Prev
    Next
    INDEX
    Explanations

    Circa, Mica, ICA, PCA, MCA

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

    The neuron activates on any token containing the letter sequence “ca.”

    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
     Secund
    -0.79
    གས་
    -0.77
     peniten
    -0.76
    ᅩ
    -0.75
    зывают
    -0.73
    nonsense
    -0.73
     Severe
    -0.73
    很喜欢
    -0.73
     furs
    -0.71
     Europeo
    -0.71
    POSITIVE LOGITS
     clipped
    0.79
    IQUES
    0.76
     shitty
    0.76
    UCA
    0.75
    relli
    0.75
     Bade
    0.74
    dia
    0.72
     ка
    0.72
    eca
    0.71
     bade
    0.71
    Activations Density 0.054%

    No Known Activations