© 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. 5853
    Prev
    Next
    INDEX
    Explanations

    impact of

    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
    ли
    1.95
     Η
    1.88
     ܗܘ
    1.83
    我们
    1.69
     ploy
    1.68
    ન
    1.68
    ко
    1.66
     paces
    1.66
    ныгы
    1.66
    चानक
    1.65
    POSITIVE LOGITS
    ara
    1.94
    ceram
    1.91
    BE
    1.75
    ant
    1.70
    CA
    1.70
    㕲
    1.70
    sony
    1.70
    empi
    1.69
    rechts
    1.66
    ्स
    1.63
    Activations Density 0.037%

    No Known Activations