© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86797
    Prev
    Next
    INDEX
    Explanations

    cassert, remission, transitive

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

    The neuron strongly activates on unusually long individual tokens (e.g. long identifiers, URLs, or multi‐syllable words).

    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
     Why
    -2.14
    dekor
    -2.03
    Surprisingly
    -2.03
     Budaya
    -2.03
    What
    -2.00
    賬
    -2.00
    ременно
    -1.98
    Why
    -1.98
     hierba
    -1.98
    Two
    -1.96
    POSITIVE LOGITS
    蹰
    2.97
    </i>
    2.45
    糴
    2.34
     Dinas
    2.19
     he
    2.09
     delightfully
    2.06
     местных
    2.02
    隄
    2.02
    냑
    2.00
    </h3>
    1.99
    Activations Density 0.001%

    No Known Activations