© 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. 22-GEMMASCOPE-RES-131K
    7. 14291
    Prev
    Next
    INDEX
    Explanations

    technical terms and code

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

    The neuron fires on SQL reserved keywords (e.g. uppercase JOIN, BY).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    [++
    -1.15
    standigheden
    -1.11
     Aún
    -1.04
     Incluye
    -1.02
     when
    -1.00
     Lleva
    -0.96
    Ĝ
    -0.96
     imprensa
    -0.96
    nitř
    -0.95
     osztály
    -0.91
    POSITIVE LOGITS
    نتیجه
    1.24
    مقاله
    1.12
    توضی
    1.11
    شكرا
    1.07
    だいぶ
    1.05
    تے
    1.04
    凄く
    1.02
    どこに
    1.02
    Wady
    1.01
    ඩ
    1.01
    Activations Density 0.000%

    No Known Activations