© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212628
    Prev
    Next
    INDEX
    Explanations

    account numbers, other villages, erasure of, encompasses multiple, various education

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

    health and biological contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    correcto
    0.48
    adres
    0.47
     界
    0.46
     адре
    0.45
    <0x94>
    0.45
     atracción
    0.45
     மக்களை
    0.45
    帅
    0.44
    лены
    0.44
     इंतजार
    0.44
    POSITIVE LOGITS
     Immigration
    0.54
     In
    0.49
     novices
    0.49
     Pharm
    0.48
     Mack
    0.47
     Hospice
    0.46
     Climate
    0.46
     Gin
    0.45
     Hari
    0.45
    INO
    0.44
    Activations Density 0.000%

    No Known Activations