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

    Neuronpedia

    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. 28769
    Prev
    Next
    INDEX
    Explanations

    powershell function

    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
    (
    0.62
    hrs
    0.52
    hattam
    0.52
    eras
    0.51
    Laz
    0.51
    OfString
    0.50
    (“
    0.50
    $(\
    0.50
    Ls
    0.50
    bees
    0.50
    POSITIVE LOGITS
    ة
    0.55
     сведения
    0.52
     buộc
    0.50
     rõ
    0.50
     fejl
    0.49
     diagnóstico
    0.48
    ین
    0.48
     distinguished
    0.47
    ষি
    0.46
     cửa
    0.46
    Activations Density 0.000%

    No Known Activations