© 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. 16-GEMMASCOPE-2-RES-262K
    7. 40714
    Prev
    Next
    INDEX
    Explanations

    proposed solution documentation

    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
    扨
    0.56
    痱
    0.55
    ২০
    0.53
     ದೊಡ್ಡ
    0.52
     یہودیوں
    0.52
     खासतौर
    0.51
    addSubview
    0.50
     السيارات
    0.50
    widgetTo
    0.50
     நிமிட
    0.50
    POSITIVE LOGITS
    4
    0.73
    5
    0.62
    0
    0.60
     disc
    0.52
     volume
    0.52
    7
    0.52
    li
    0.50
    l
    0.49
     phone
    0.48
    6
    0.48
    Activations Density 0.000%

    No Known Activations