© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 98749
    Prev
    Next
    INDEX
    Explanations

    heterogeneity / diversity

    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
     listas
    0.44
     lists
    0.43
     eval
    0.41
     depends
    0.40
    妣
    0.39
    周围
    0.39
     ملعب
    0.39
     比
    0.38
     لیست
    0.38
     prist
    0.37
    POSITIVE LOGITS
     heterogeneity
    1.41
     heterogeneous
    1.38
     homogeneity
    1.13
     homogenous
    1.13
     diversity
    1.12
     homogeneous
    1.09
     inhomogeneity
    1.06
    diversity
    1.05
    Diversity
    1.05
     inhomogeneous
    1.05
    Activations Density 0.000%

    No Known Activations