© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15297
    Prev
    Next
    INDEX
    Explanations

    book title, citation, metadata

    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
    nms
    0.40
    轲
    0.39
     yazı
    0.39
     shameless
    0.39
     KPIs
    0.38
    dataSet
    0.38
    myX
    0.38
     చర్చ
    0.38
     lleve
    0.38
     destek
    0.37
    POSITIVE LOGITS
     OCLC
    0.51
    名稱
    0.50
     Blu
    0.42
    Donor
    0.41
    Blu
    0.39
    據
    0.39
    Description
    0.38
    長
    0.38
    Genre
    0.38
    Manufacturer
    0.38
    Activations Density 0.014%

    No Known Activations