© 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. 61659
    Prev
    Next
    INDEX
    Explanations

    every movement

    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
     uses
    0.49
     implements
    0.48
     Layer
    0.46
     Occupational
    0.46
     diagrams
    0.46
    '
    0.46
     Cyt
    0.45
     terminology
    0.45
     fibrosis
    0.45
     Sem
    0.44
    POSITIVE LOGITS
     سرکاری
    0.47
    erté
    0.46
     अफसरों
    0.45
    而且
    0.44
    ników
    0.44
    ovaný
    0.44
    öffent
    0.43
    徇
    0.43
    MODKEY
    0.42
     singolo
    0.41
    Activations Density 0.006%

    No Known Activations