© 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. 46554
    Prev
    Next
    INDEX
    Explanations

    checklist items

    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
     пъ
    0.42
    дови
    0.40
     lumineux
    0.40
    ве
    0.40
    ’-
    0.39
    ver
    0.39
    exceptions
    0.39
     exceptions
    0.39
    ᾿
    0.39
    Ве
    0.38
    POSITIVE LOGITS
     Dysfunction
    0.44
     want
    0.43
    繁殖
    0.43
    兼用
    0.42
     desired
    0.42
     struggle
    0.41
    監視
    0.41
     مطم
    0.41
     dysfunction
    0.41
     desire
    0.41
    Activations Density 0.008%

    No Known Activations