© 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. 41-GEMMASCOPE-2-RES-262K
    7. 24487
    Prev
    Next
    INDEX
    Explanations

    equal distribution

    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_all/layer_41_width_262k_l0_big
    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
    চ্য
    0.39
    ඟ
    0.39
    specificity
    0.38
    SelectSingle
    0.37
     cdot
    0.37
    bant
    0.37
     discontinuities
    0.37
    攘
    0.36
    ้น
    0.36
    िले
    0.36
    POSITIVE LOGITS
     equally
    2.25
     equal
    2.09
     evenly
    1.95
     Equal
    1.93
    Equal
    1.84
     Equally
    1.82
     equalize
    1.76
    equal
    1.74
     সমান
    1.71
     eşit
    1.70
    Activations Density 0.007%

    No Known Activations