© 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. 117753
    Prev
    Next
    INDEX
    Explanations

    Oscar winners

    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
    Мы
    0.76
    Все
    0.75
    گ
    0.75
    Если
    0.73
    ),
    0.71
    suffixes
    0.71
    Σ
    0.70
    ushes
    0.69
    Το
    0.69
    Тем
    0.67
    POSITIVE LOGITS
     \#
    0.80
     He
    0.76
     P
    0.75
     ï
    0.73
     I
    0.69
     l
    0.68
     Resource
    0.68
     G
    0.67
     použití
    0.66
     Be
    0.65
    Activations Density 0.000%

    No Known Activations