© 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. 16-GEMMASCOPE-2-RES-262K
    7. 42957
    Prev
    Next
    INDEX
    Explanations

    middle-aged or middle-class

    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
     are
    1.41
    ال
    1.14
    ED
    1.07
     êtes
    1.07
    あ
    1.07
    ।
    1.05
    いた
    1.05
    ی
    1.03
    两
    1.03
    ⺀
    1.02
    POSITIVE LOGITS
    -
    1.57
    </h2>
    0.95
    ↵
    0.92
    jaman
    0.90
     by
    0.89
    0.85
    ীয়
    0.84
    ীয়
    0.83
     reorganization
    0.82
     depolarization
    0.82
    Activations Density 0.005%

    No Known Activations