© 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. 31-GEMMASCOPE-2-RES-262K
    7. 41883
    Prev
    Next
    INDEX
    Explanations

    declaration of type

    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_31_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
     использовании
    0.52
     Sodium
    0.52
     Aerospace
    0.46
     пласти
    0.46
     Physi
    0.45
     использова
    0.44
     «
    0.43
     আৰ
    0.43
    Sodium
    0.42
     صغيرة
    0.42
    POSITIVE LOGITS
     जिससे
    0.46
    抬
    0.41
     sabem
    0.40
    ตาย
    0.40
    มน
    0.40
    มากมาย
    0.39
    महल
    0.39
    不止
    0.39
    ซึ่ง
    0.38
    atedral
    0.38
    Activations Density 0.001%

    No Known Activations