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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3638
    Prev
    Next
    INDEX
    Explanations

    EU, Union, or unions

    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_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
    يك
    1.93
    ◽
    1.80
     EMI
    1.80
     IPs
    1.76
    ח
    1.73
    мене
    1.73
    ब्दिक
    1.73
    }$}
    1.72
    ために
    1.70
    서는
    1.70
    POSITIVE LOGITS
    لین
    2.03
    em
    2.02
    er
    1.98
    от
    1.94
    irà
    1.92
     δεί
    1.91
    aq
    1.81
    alten
    1.81
     dépens
    1.79
    ει
    1.78
    Activations Density 0.107%

    No Known Activations