© 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. 51199
    Prev
    Next
    INDEX
    Explanations

    term that, permit from, plate ., disgusting because, important (

    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
     universities
    0.49
     University
    0.48
    University
    0.47
     popularly
    0.47
     smuggling
    0.46
    '
    0.46
    Ko
    0.46
     shipping
    0.46
    Dü
    0.46
    (
    0.45
    POSITIVE LOGITS
    CDCl
    0.52
     "&
    0.51
     vostra
    0.49
     Limitations
    0.48
     ω
    0.47
    ڑوں
    0.47
     让
    0.47
    reflectionMap
    0.47
     '&
    0.47
    descripcion
    0.46
    Activations Density 0.012%

    No Known Activations