© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 86593
    Prev
    Next
    INDEX
    Explanations

    trampoline park

    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
     सोते
    0.60
     dissipation
    0.59
     temperatura
    0.57
     chromatography
    0.57
    ❘
    0.56
     зависимости
    0.56
     voltaje
    0.56
     tensione
    0.55
    ко
    0.54
    ]=-
    0.54
    POSITIVE LOGITS
     
    0.54
    ag
    0.50
    ان
    0.49
    న్స్
    0.49
    ilta
    0.47
    akov
    0.47
    munk
    0.47
    re
    0.47
    使用
    0.47
    ilot
    0.46
    Activations Density 0.000%

    No Known Activations