© 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. 52632
    Prev
    Next
    INDEX
    Explanations

    database connector names

    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
    ("|
    0.41
    Vitamin
    0.39
     epoch
    0.38
    ROLL
    0.38
     Fireworks
    0.37
     і
    0.37
    हमने
    0.37
    Common
    0.36
     हमने
    0.36
     Industry
    0.36
    POSITIVE LOGITS
    ликт
    0.45
    abhuto
    0.43
     pê
    0.41
    xido
    0.41
    鵝
    0.40
    ով
    0.39
     faciles
    0.39
     bhavanti
    0.38
    सिक
    0.38
    inct
    0.38
    Activations Density 0.008%

    No Known Activations