© 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. 40-GEMMASCOPE-2-RES-65K
    7. 55643
    Prev
    Next
    INDEX
    Explanations

    entity resolution, record linkage

    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_40_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
    def
    0.43
     approvals
    0.43
     ^
    0.42
     Monica
    0.42
    Dictionary
    0.40
     mett
    0.40
     permissions
    0.39
     g
    0.39
     defenses
    0.39
     world
    0.38
    POSITIVE LOGITS
    ရော
    0.44
    lineNumber
    0.43
    疥
    0.43
    ုတ်
    0.43
    원본파일명
    0.41
    㴡
    0.40
    ğan
    0.40
    وقف
    0.40
     Köz
    0.40
    fNil
    0.40
    Activations Density 0.006%

    No Known Activations