© 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. 17973
    Prev
    Next
    INDEX
    Explanations

    besides, apart from, aside from

    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
     aide
    0.40
    Drain
    0.39
     Sul
    0.39
    Kam
    0.38
    Y
    0.38
    Heart
    0.38
    Assistant
    0.38
     टीमों
    0.38
     Aide
    0.38
    ON
    0.37
    POSITIVE LOGITS
    メリカ
    0.53
    ға
    0.41
    لسط
    0.40
     své
    0.40
     المغرب
    0.39
    Ꮑ
    0.38
     мира
    0.38
    vature
    0.38
     महाराष्ट्रा
    0.38
    ЛЯ
    0.38
    Activations Density 0.001%

    No Known Activations