© 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-262K
    7. 6614
    Prev
    Next
    INDEX
    Explanations

    area names and regions

    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
    сных
    0.90
    CLES
    0.87
     nondegenerate
    0.84
    ﭜ
    0.84
    úd
    0.84
     demonstr
    0.83
     seep
    0.81
    𝐡
    0.80
     preju
    0.80
    ణ
    0.80
    POSITIVE LOGITS
    I
    0.75
    setName
    0.71
    ariu
    0.70
    la
    0.66
    انہوں
    0.66
    awie
    0.66
    ถุนายน
    0.65
    för
    0.64
    agate
    0.63
    اعری
    0.63
    Activations Density 0.000%

    No Known Activations