© 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. 44443
    Prev
    Next
    INDEX
    Explanations

    有什么好

    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
    ୬
    1.00
    მდეგ
    0.98
    ੫
    0.92
    ковый
    0.91
    湋
    0.89
     Jadeja
    0.88
    ேத்க
    0.87
    ୮
    0.87
    ੦
    0.87
     नए
    0.86
    POSITIVE LOGITS
     au
    0.74
    M
    0.74
     oc
    0.70
    ud
    0.70
    ни
    0.68
     живо
    0.66
    ik
    0.65
    ка
    0.64
     настрой
    0.64
    Q
    0.63
    Activations Density 0.000%

    No Known Activations