© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7486
    Prev
    Next
    INDEX
    Explanations

    reply to specific instructions

    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
     morbidity
    1.71
    ଆ
    1.66
     afar
    1.66
    kých
    1.65
    ת
    1.65
     myopia
    1.63
    瞍
    1.63
     palpitations
    1.63
    uous
    1.62
    ﺓ
    1.59
    POSITIVE LOGITS
    g
    2.25
    re
    2.06
    ter
    1.78
    assing
    1.78
    nder
    1.77
    od
    1.72
    gd
    1.71
    ce
    1.66
    te
    1.66
    gger
    1.66
    Activations Density 0.071%

    No Known Activations