© 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. 40-GEMMASCOPE-2-RES-262K
    7. 461
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    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_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
     فِي
    0.37
    දු
    0.37
    !”,
    0.37
    !’
    0.36
     حدیث
    0.36
    LOW
    0.36
     계산
    0.35
    窮
    0.35
    dom
    0.35
     подроб
    0.35
    POSITIVE LOGITS
     Above
    0.46
     हमने
    0.43
     Uses
    0.41
     above
    0.40
     Access
    0.40
     `<
    0.39
     noqa
    0.39
     ABV
    0.39
     "<
    0.39
     первая
    0.39
    Activations Density 0.000%

    No Known Activations