© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 205060
    Prev
    Next
    INDEX
    Explanations

    "Tu" vs "você"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    сы
    0.41
    තුරු
    0.41
     pertence
    0.41
     പുതിയ
    0.39
    ቹ
    0.39
    蝣
    0.39
     expires
    0.39
     ifelse
    0.38
     sydney
    0.38
    िद
    0.38
    POSITIVE LOGITS
     altru
    0.43
    抵抗
    0.40
    提到
    0.39
    issionais
    0.38
     Exact
    0.38
    窑
    0.37
     पू
    0.37
     அழு
    0.37
     distraught
    0.37
    手
    0.37
    Activations Density 0.001%

    No Known Activations