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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10090
    Prev
    Next
    INDEX
    Explanations

    poem requests

    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_12_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
    ف
    1.81
     ее
    1.54
     weiß
    1.54
     أيضاً
    1.54
     ausschließlich
    1.53
    ا
    1.49
     œuvres
    1.48
    го
    1.47
    Elems
    1.46
     трех
    1.45
    POSITIVE LOGITS
    ak
    2.22
     sanc
    1.88
    ﺑ
    1.86
    ل
    1.84
    াল
    1.81
    ﻳ
    1.76
    ஞர்
    1.74
    UL
    1.66
    hect
    1.66
     sii
    1.66
    Activations Density 0.036%

    No Known Activations