© 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. 10-GEMMASCOPE-RES-131K
    7. 10519
    Prev
    Next
    INDEX
    Explanations

    advance voting, sheets, payment, warfare, funds

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

    The neuron fires on occurrences of the root “advanc” (e.g. “Advance,” “advancements,” etc.).

    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
    _
    -3.38
    }$
    -3.03
    s
    -2.59
    2
    -2.33
    気づ
    -2.22
     the
    -2.16
     Problemen
    -2.13
    輝く
    -2.11
    jenigen
    -2.11
     várias
    -2.11
    POSITIVE LOGITS
    ↵
    3.63
     selben
    2.58
    呖
    2.47
     оригіналу
    2.42
    Благодаря
    2.36
    Наши
    2.34
    噏
    2.34
    ｌ
    2.33
    了一种
    2.31
    які
    2.28
    Activations Density 0.009%

    No Known Activations