© 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. 8161
    Prev
    Next
    INDEX
    Explanations

    finally summing up

    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
     and
    0.82
    và
    0.66
    and
    0.66
     وت
    0.65
    ','
    0.65
     και
    0.63
     Its
    0.63
    ´
    0.62
     ,
    0.61
    Its
    0.61
    POSITIVE LOGITS
    等等
    1.38
     ultimately
    1.30
     uiteindelijk
    1.21
     etc
    1.20
     whatnot
    1.20
     ইত্যাদি
    1.19
     crucially
    1.16
     downright
    1.15
     sebagainya
    1.15
     sogar
    1.13
    Activations Density 0.491%

    No Known Activations