© 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. 1813
    Prev
    Next
    INDEX
    Explanations

    pound, nudge, minigame, adultery, Russian, Catalan

    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
    ி
    0.67
     Catawiki
    0.61
     Autodesk
    0.55
    วัสดี
    0.55
     momencie
    0.54
    場合には
    0.53
    করিয়া
    0.53
    ی
    0.53
     می
    0.52
    大丈夫
    0.52
    POSITIVE LOGITS
    olines
    0.52
    oming
    0.51
    uyor
    0.49
    çal
    0.49
    ām
    0.49
    omon
    0.49
    omed
    0.48
    ulse
    0.48
    olič
    0.48
    ానిక
    0.47
    Activations Density 0.613%

    No Known Activations