© 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. 34-GEMMASCOPE-RES-131K
    4. 103448
    Prev
    Next
    INDEX
    Explanations

    of [noun]

    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_34/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
     séjours
    -0.99
     achats
    -0.98
     ayur
    -0.93
     qualités
    -0.92
    などが
    -0.91
     prochaines
    -0.90
     manières
    -0.90
     goûts
    -0.89
    囫
    -0.86
     déplacements
    -0.86
    POSITIVE LOGITS
     dreams
    1.09
     doom
    1.01
     sehr
    0.98
     oportunidades
    0.97
     mín
    0.94
     juta
    0.94
     impacto
    0.93
     despair
    0.90
     sufficient
    0.89
     lás
    0.88
    Activations Density 0.034%

    No Known Activations