© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48210
    Prev
    Next
    INDEX
    Explanations

    shorts and associated types

    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
    ”)
    0.66
    ти
    0.64
    ва
    0.63
    nego
    0.63
    organization
    0.63
    ت
    0.62
    т
    0.61
     organization
    0.61
    こと
    0.59
     l
    0.57
    POSITIVE LOGITS
    m
    0.71
     цик
    0.68
     যেটি
    0.61
    ED
    0.59
     BEACH
    0.59
    ।
    0.59
    मार्
    0.58
     PRC
    0.56
     JULY
    0.56
     کاروبار
    0.56
    Activations Density 0.002%

    No Known Activations