© 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. 9302
    Prev
    Next
    INDEX
    Explanations

    relation between things

    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
    保证
    0.50
    2
    0.49
    声
    0.45
    就
    0.44
    居
    0.43
    Д
    0.42
    拉
    0.42
    内
    0.42
    (),
    0.42
    4
    0.42
    POSITIVE LOGITS
     hordes
    0.50
     exuber
    0.49
     vultures
    0.48
     Scor
    0.47
     Ambros
    0.46
     floods
    0.46
     خوان
    0.45
     composers
    0.45
     kompos
    0.45
     exalted
    0.45
    Activations Density 0.013%

    No Known Activations