© 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. 31-GEMMASCOPE-2-RES-16K
    7. 16353
    Prev
    Next
    INDEX
    Explanations

    first, first step, initial

    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_31_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
    udio
    0.49
    żeli
    0.49
    ②
    0.47
    ➋
    0.46
    ቓ
    0.45
    ujan
    0.44
     II
    0.43
    ^*
    0.43
    पन
    0.43
    udia
    0.42
    POSITIVE LOGITS
     first
    4.06
     første
    3.98
     första
    3.86
    first
    3.78
     pertama
    3.78
     eerste
    3.75
     ensimmä
    3.70
     primeira
    3.56
     первый
    3.56
     erste
    3.55
    Activations Density 0.430%

    No Known Activations