© 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. 51431
    Prev
    Next
    INDEX
    Explanations

    versioning, if needed

    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
    瑢
    0.46
     constructor
    0.43
    kova
    0.42
    钀
    0.41
    door
    0.41
     оборудования
    0.41
     interrupts
    0.40
     Equipment
    0.40
    闼
    0.40
    pital
    0.40
    POSITIVE LOGITS
    łym
    0.50
     আমি
    0.50
    infested
    0.48
     بود
    0.46
    aqueous
    0.46
    銹
    0.46
     dyst
    0.45
    SCAPE
    0.45
    unicode
    0.44
     uphe
    0.44
    Activations Density 0.002%

    No Known Activations