© 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. 31-GEMMASCOPE-2-RES-65K
    7. 63870
    Prev
    Next
    INDEX
    Explanations

    date, expires, time, weight, term

    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
    로
    0.50
     Planta
    0.49
     articoli
    0.47
     integrado
    0.47
     將
    0.45
     произо
    0.45
     locis
    0.45
    responder
    0.45
     anniversary
    0.44
     présente
    0.43
    POSITIVE LOGITS
     жал
    0.45
     പക്ഷ
    0.44
     सौरभ
    0.40
    empot
    0.40
    篒
    0.40
    ogical
    0.40
     žal
    0.40
    Ranges
    0.39
    igable
    0.39
     पाती
    0.39
    Activations Density 0.017%

    No Known Activations