© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68737
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     momentan
    -1.02
     amalgamation
    -1.00
    姦
    -0.90
     sogen
    -0.90
    🪛
    -0.89
     הַ
    -0.89
     infographics
    -0.89
    arande
    -0.87
    nid
    -0.86
     actuellement
    -0.85
    POSITIVE LOGITS
     but
    1.17
     cuivre
    1.13
    سپ
    1.09
    DAFTAR
    1.08
     cansado
    1.07
     even
    1.05
     cerdo
    1.04
    吅
    1.03
     bocas
    1.03
     dedicado
    1.02
    Activations Density 0.018%

    No Known Activations