© 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-262K
    7. 250821
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    𝘭
    0.48
    ceramic
    0.47
    linearity
    0.46
    screen
    0.45
    sodium
    0.44
    AllFilesIn
    0.44
     керами
    0.44
    bracketing
    0.43
    pod
    0.43
    salmon
    0.43
    POSITIVE LOGITS
     Zürich
    0.49
     koristi
    0.47
    ม
    0.46
    ällä
    0.45
     piv
    0.45
     Isto
    0.45
    म
    0.44
     lent
    0.44
     reag
    0.43
     Tourist
    0.43
    Activations Density 0.003%

    No Known Activations