© 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. 1690
    Prev
    Next
    INDEX
    Explanations

    punctuation and grammar particles

    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
     $\{\
    0.47
    y
    0.46
    ҳои
    0.45
    서
    0.44
    PNG
    0.42
    ®.
    0.42
    Mehr
    0.42
     keltiradi
    0.42
     relevant
    0.41
    竴
    0.41
    POSITIVE LOGITS
     는
    0.75
     부터
    0.70
     ,
    0.69
     으로
    0.66
     は
    0.64
     까지
    0.62
     から
    0.62
     లు
    0.62
     を
    0.61
     が
    0.61
    Activations Density 0.314%

    No Known Activations