© 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. 6012
    Prev
    Next
    INDEX
    Explanations

    diffusion models and transformers

    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
    тся
    1.09
    ahati
    1.03
    ों
    1.02
    ৯
    1.02
    NEC
    0.99
    ात
    0.97
    اً
    0.97
    BPACK
    0.97
    ಣೆ
    0.95
    ó
    0.94
    POSITIVE LOGITS
     изучения
    1.01
     хорошее
    1.01
    load
    1.00
    逆に
    0.97
     ofthe
    0.96
    its
    0.95
    steal
    0.95
    .}
    0.95
     elle
    0.94
     allerlei
    0.94
    Activations Density 0.065%

    No Known Activations