© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17282
    Prev
    Next
    INDEX
    Explanations

    city, postal code, country, district

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    норий
    0.48
     গড়ে
    0.44
     incarceration
    0.44
     charity
    0.43
     crafting
    0.43
    䒩
    0.42
     courthouse
    0.41
     stewardship
    0.41
     Charities
    0.40
     разрабо
    0.40
    POSITIVE LOGITS
    _{
    0.47
    baixo
    0.46
    🥰
    0.42
     Cod
    0.42
     COD
    0.41
    Cod
    0.41
    CH
    0.40
     Uzbekistan
    0.40
     Velcro
    0.40
    COD
    0.40
    Activations Density 0.005%

    No Known Activations