© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9680
    Prev
    Next
    INDEX
    Explanations

    links and data processing

    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_40_width_16k_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
    悼
    0.41
    camouflage
    0.41
     Salmonella
    0.40
     Saskatoon
    0.39
    gstatic
    0.38
    吞
    0.38
    ভাস
    0.38
    逮
    0.38
    Fraction
    0.38
    Alberta
    0.38
    POSITIVE LOGITS
     breakout
    0.43
    ructions
    0.38
     breakouts
    0.38
    править
    0.37
     approximate
    0.36
    ipient
    0.36
    weeney
    0.36
    ’”
    0.36
    迎来
    0.36
    fileobj
    0.35
    Activations Density 0.023%

    No Known Activations