© 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. 4089
    Prev
    Next
    INDEX
    Explanations

    either A or B

    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
    ться
    2.22
    ção
    2.03
    tı
    2.02
    il
    1.98
    ść
    1.88
    ט
    1.88
    är
    1.80
    ruta
    1.78
    یت
    1.77
    ﺐ
    1.77
    POSITIVE LOGITS
    ли
    1.75
     neighboring
    1.61
    র
    1.61
    {~
    1.55
    ان
    1.51
    ра
    1.49
    الإ
    1.48
    ار
    1.46
    च्या
    1.44
    на
    1.40
    Activations Density 0.039%

    No Known Activations