© 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. 22-GEMMASCOPE-RES-131K
    4. 40017
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    𖣘
    -1.29
    𖣔
    -1.23
    𖧵
    -1.23
     menyen
    -1.16
    ։
    -1.13
     стоковые
    -1.13
    是
    -1.12
     kalt
    -1.12
     to
    -1.09
     minimalis
    -1.05
    POSITIVE LOGITS
    ⽅
    1.21
     today
    1.20
     impresionantes
    1.08
     Hinsicht
    1.07
     hermosas
    1.06
    気軽
    1.06
    żna
    1.05
     niedriger
    1.04
     гораздо
    1.04
     latter
    1.04
    Activations Density 0.000%

    No Known Activations