© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 12778
    Prev
    Next
    INDEX
    Explanations

    sequences ending in `ai`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    sız
    0.68
     교
    0.65
    opolymer
    0.63
     Kitt
    0.62
     opposition
    0.62
     질
    0.62
    ohydro
    0.61
    izion
    0.60
    ظيف
    0.59
    ancock
    0.58
    POSITIVE LOGITS
    StartZ
    0.79
    indelijk
    0.76
    捲
    0.74
     rosé
    0.74
    પ્ર
    0.74
     mering
    0.73
     gula
    0.73
    <unused1033>
    0.72
    energ
    0.71
     larch
    0.70
    Activations Density 0.230%

    No Known Activations