© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1048
    Prev
    Next
    INDEX
    Explanations

    computing and technical terms

    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_16_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
     prur
    0.54
    _
    0.54
     unworthy
    0.53
     scammers
    0.52
    ByName
    0.50
     zyg
    0.49
     supernatant
    0.49
    woofer
    0.49
    不会
    0.48
     =-\
    0.48
    POSITIVE LOGITS
    კო
    0.53
     aprile
    0.51
    ید
    0.51
     HOTEL
    0.50
     Hoa
    0.48
     Airline
    0.48
     Flughafen
    0.48
    開発
    0.48
     JAPAN
    0.47
     Ahead
    0.47
    Activations Density 0.000%

    No Known Activations