© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56240
    Prev
    Next
    INDEX
    Explanations

    neurons and connections

    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
    f
    0.51
    in
    0.50
     rangkaian
    0.47
    and
    0.46
    m
    0.45
    ad
    0.43
    Valid
    0.42
     adventurous
    0.41
    o
    0.40
    다
    0.40
    POSITIVE LOGITS
     Menschen
    0.47
     شدید
    0.46
    性は
    0.45
     symplect
    0.45
     gering
    0.44
    byterian
    0.44
    នុ
    0.44
    ₵
    0.43
    铣
    0.43
     المسي
    0.42
    Activations Density 0.017%

    No Known Activations