© 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. 12-GEMMASCOPE-2-RES-262K
    7. 10943
    Prev
    Next
    INDEX
    Explanations

    go to

    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_12_width_262k_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
     bảy
    0.75
    들
    0.73
    BLY
    0.73
    इकिल
    0.71
     Raghav
    0.70
    ৃত্ব
    0.68
    ’
    0.68
    ed
    0.68
    Instance
    0.66
    CNT
    0.66
    POSITIVE LOGITS
    нибудь
    0.87
     कोई
    0.84
    𝙠
    0.84
     your
    0.82
     yourself
    0.82
     mountainous
    0.82
     bikini
    0.80
     mindfulness
    0.80
    aways
    0.79
    他の
    0.78
    Activations Density 0.071%

    No Known Activations