© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28965
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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_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
     Dharmendra
    0.45
     LAYER
    0.43
     spelen
    0.42
    Ỹ
    0.42
    gameObjects
    0.42
     Jepang
    0.40
     phenotypes
    0.40
     ujung
    0.40
    āl
    0.40
    álni
    0.39
    POSITIVE LOGITS
    e
    0.41
     en
    0.40
    yn
    0.40
     فقد
    0.39
     over
    0.39
     mi
    0.39
     中的
    0.39
     Cultura
    0.38
     دان
    0.38
     Culture
    0.38
    Activations Density 0.001%

    No Known Activations