© 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. 40-GEMMASCOPE-2-RES-262K
    7. 194212
    Prev
    Next
    INDEX
    Explanations

    schema definition, data types

    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_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
    ndes
    0.47
    iales
    0.42
    颔
    0.40
    slug
    0.39
    istel
    0.39
     GQ
    0.39
    illa
    0.39
    θ
    0.38
    मिता
    0.38
     ಮೀ
    0.38
    POSITIVE LOGITS
    稷
    0.41
     geopol
    0.38
    errorMessage
    0.38
    бой
    0.38
     geometri
    0.38
     впечат
    0.37
    codingPath
    0.36
    ъм
    0.36
     pegatina
    0.35
    煉
    0.35
    Activations Density 0.022%

    No Known Activations