© 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. 12490
    Prev
    Next
    INDEX
    Explanations

    routes and navigation components

    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
    rod
    0.49
    Plate
    0.46
    storybook
    0.44
    ri
    0.43
    l
    0.42
    Acetic
    0.42
    ボン
    0.41
    Asie
    0.41
    Hospital
    0.41
    EMPL
    0.41
    POSITIVE LOGITS
     calle
    0.43
     내
    0.43
     path
    0.42
     treaties
    0.42
     go
    0.41
    将
    0.41
    न्दावन
    0.40
     value
    0.40
     name
    0.40
     ইন্
    0.40
    Activations Density 0.001%

    No Known Activations