Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 5360
    Prev
    Next
    INDEX
    Explanations

    virtually

    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_16_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
     couvre
    0.63
    ov
    0.62
     montée
    0.57
     falsa
    0.57
     leggera
    0.57
    u
    0.57
     براي
    0.56
    ವರಿಗೆ
    0.55
     correg
    0.55
     ľudí
    0.55
    POSITIVE LOGITS
    0
    0.59
    vaient
    0.53
    9
    0.50
    没有
    0.47
    puts
    0.47
    ются
    0.46
    劳
    0.46
    stood
    0.46
    ᵍ
    0.45
    成功
    0.45
    Activations Density 0.000%

    No Known Activations