© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48054
    Prev
    Next
    INDEX
    Explanations

    SAC, Rate, CTR, Red

    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
    1.10
    ights
    1.03
    us
    0.95
    il
    0.90
    ors
    0.87
    CK
    0.87
    ost
    0.84
    es
    0.83
    upp
    0.83
    یس
    0.83
    POSITIVE LOGITS
     lesión
    0.82
    να
    0.81
    ні
    0.80
    心
    0.77
     vál
    0.76
    ：
    0.75
     administración
    0.74
    在
    0.74
    流通
    0.74
    эн
    0.73
    Activations Density 0.000%

    No Known Activations