© 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. 28987
    Prev
    Next
    INDEX
    Explanations

    new, other, different

    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
    组织
    0.48
     pesticides
    0.44
    促进
    0.43
    組織
    0.43
    政府
    0.41
    牲
    0.41
    лил
    0.41
    样
    0.41
     практику
    0.40
    군은
    0.40
    POSITIVE LOGITS
     nye
    0.51
     neues
    0.46
     novas
    0.46
     nieuwe
    0.45
     another
    0.45
     one
    0.45
     Widers
    0.44
     edition
    0.44
    ття
    0.43
     nuovi
    0.43
    Activations Density 0.024%

    No Known Activations