© 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. 108682
    Prev
    Next
    INDEX
    Explanations

    token followed by specific word

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

    The neuron lights up on tokens from formal legal‐opinion text, effectively spotting bits of a court judgment.

    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
    了口气
    -0.98
     keindahan
    -0.96
    leta
    -0.92
     حتی
    -0.92
     our
    -0.84
    ruckt
    -0.84
    तम
    -0.83
    hithe
    -0.82
    Ṛ
    -0.81
     gelar
    -0.81
    POSITIVE LOGITS
     things
    0.92
     näher
    0.86
    見て
    0.83
    Formik
    0.80
    cidade
    0.80
    ϒ
    0.80
    had
    0.79
    illow
    0.78
     Rückkehr
    0.78
    Fisch
    0.78
    Activations Density 0.000%

    No Known Activations