© 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. 15580
    Prev
    Next
    INDEX
    Explanations

    documentation validation

    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
    ி
    0.65
    ymmetrical
    0.58
    aktif
    0.57
    ന്തപു
    0.56
    otype
    0.55
    ândia
    0.55
    iology
    0.54
    ș
    0.54
    ypes
    0.54
    వీ
    0.53
    POSITIVE LOGITS
    というのが
    0.66
    ต่างๆ
    0.64
     त्यामुळे
    0.61
     ಎಂಬುದ
    0.61
    指的是
    0.61
    ということは
    0.60
     என்பது
    0.59
    のかもし
    0.58
     ہوں۔
    0.57
     tersebut
    0.57
    Activations Density 0.611%

    No Known Activations