© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2240
    Prev
    Next
    INDEX
    Explanations

    ideological AI

    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_16_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
    in
    0.75
    id
    0.73
    m
    0.67
     can
    0.60
     building
    0.57
    c
    0.57
    S
    0.56
    ie
    0.55
     University
    0.54
     people
    0.54
    POSITIVE LOGITS
     okazji
    0.64
     sidste
    0.64
    Ꮢ
    0.63
     senaste
    0.62
    ，
    0.62
    Ꮭ
    0.62
     activiteiten
    0.61
    ،
    0.61
     livelli
    0.60
     असलेल्या
    0.59
    Activations Density 1.812%

    No Known Activations