© 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. 40-GEMMASCOPE-2-RES-65K
    7. 49012
    Prev
    Next
    INDEX
    Explanations

    Peterson, Pearson, Robertson, Hanson

    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_40_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
    礡
    0.43
    是一
    0.39
    sers
    0.39
    みた
    0.38
     powsta
    0.38
     dynamism
    0.36
     आस
    0.35
    bacher
    0.35
    ζεται
    0.35
    ร้อน
    0.34
    POSITIVE LOGITS
    হ
    0.43
     Usted
    0.43
    последствии
    0.42
    òi
    0.42
     !,
    0.41
    least
    0.39
     !",
    0.39
    ÷
    0.38
     Scandin
    0.38
     sonido
    0.38
    Activations Density 0.011%

    No Known Activations