© 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. 45260
    Prev
    Next
    INDEX
    Explanations

    Tal- prefix

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

    The neuron fires on any token containing the substring “Tal,” typically in proper names or place names.

    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
    ↵
    -2.63
    鏨
    -2.58
    ;
    -2.48
    ll
    -2.45
     था
    -2.42
     These
    -2.41
    哢
    -2.39
    ᳝
    -2.30
    They
    -2.27
    灕
    -2.25
    POSITIVE LOGITS
    )
    3.00
     was
    2.80
    鹋
    2.59
    .”
    2.58
    鮰
    2.45
     帅气
    2.42
    蚨
    2.39
    瓩
    2.36
    箝
    2.36
     to
    2.36
    Activations Density 0.007%

    No Known Activations