© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 1996
    Prev
    Next
    INDEX
    Explanations

    deel mijn, heb een

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    0.54
     cujo
    0.44
    7
    0.42
     law
    0.42
    0
    0.41
    ations
    0.41
     lawyers
    0.40
     clerk
    0.39
     arba
    0.39
     John
    0.38
    POSITIVE LOGITS
     પણ
    0.53
     deswegen
    0.53
    У
    0.52
    對
    0.52
    م
    0.49
     По
    0.47
     শিক্ষ
    0.47
     সে
    0.46
    Раз
    0.46
     снима
    0.46
    Activations Density 0.000%

    No Known Activations