© 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. 109084
    Prev
    Next
    INDEX
    Explanations

    html template urls

    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
    foration
    0.71
    র
    0.68
    entin
    0.68
    ier
    0.67
    okkal
    0.65
    lte
    0.65
    ado
    0.65
    affold
    0.64
    iert
    0.64
    𝙧
    0.64
    POSITIVE LOGITS
     gü
    0.94
    고
    0.94
    त
    0.91
    า
    0.88
    ि
    0.87
    ة
    0.87
    ท
    0.87
    е
    0.86
    ת
    0.86
    та
    0.85
    Activations Density 0.001%

    No Known Activations