© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15979
    Prev
    Next
    INDEX
    Explanations

    until a condition is met

    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
    加快
    0.59
    uman
    0.58
     xong
    0.57
    ృద్ధి
    0.57
     уж
    0.56
    े
    0.56
     &
    0.55
    ああ
    0.55
    initial
    0.55
    ovington
    0.55
    POSITIVE LOGITS
     recently
    0.71
     jumpa
    0.70
    ्रम
    0.68
    近日
    0.66
    recently
    0.64
     reluctantly
    0.63
     biodegradable
    0.63
     riječi
    0.61
     Recently
    0.60
    ্ধ্য
    0.59
    Activations Density 0.075%

    No Known Activations