© 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-16K
    7. 13616
    Prev
    Next
    INDEX
    Explanations

    SQL commands

    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_16k_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
    한편
    0.62
    පු
    0.56
    жни
    0.54
    Meanwhile
    0.54
    сный
    0.54
    Giov
    0.54
    此同时
    0.54
    繳
    0.54
    <unused100>
    0.53
    сного
    0.53
    POSITIVE LOGITS
     there
    0.63
     don
    0.57
    there
    0.55
     See
    0.55
     There
    0.54
     O
    0.53
     الأمر
    0.53
     P
    0.52
    lerde
    0.50
     Don
    0.49
    Activations Density 0.498%

    No Known Activations