© 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. 44318
    Prev
    Next
    INDEX
    Explanations

    can't wait

    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
    se
    1.01
     fijo
    0.98
     aisl
    0.97
    ko
    0.96
     některé
    0.95
    iak
    0.95
    fta
    0.94
    ﮑ
    0.94
     cuant
    0.94
    esha
    0.93
    POSITIVE LOGITS
    б
    1.24
    ্ট
    1.16
    д
    1.04
    ل
    1.02
    వ
    1.02
    所以
    1.01
    Xét
    0.97
    ঈশ্বর
    0.96
     όμως
    0.95
    Haw
    0.95
    Activations Density 0.020%

    No Known Activations