© 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-65K
    7. 39802
    Prev
    Next
    INDEX
    Explanations

    visas, compliant, US company

    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_65k_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
    ocht
    0.47
     steeds
    0.46
     नए
    0.46
     aldrig
    0.45
     નવી
    0.45
    碖
    0.45
    ースト
    0.44
     nuove
    0.44
    تبط
    0.44
    遢
    0.44
    POSITIVE LOGITS
     congratulations
    0.46
    5
    0.46
    0
    0.44
     humans
    0.42
     humour
    0.42
     previously
    0.41
     PNS
    0.41
     contributing
    0.40
     Humans
    0.40
    Humans
    0.40
    Activations Density 0.010%

    No Known Activations