© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19380
    Prev
    Next
    INDEX
    Explanations

    under specific conditions or supervision

    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_31_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
    ى
    0.87
    m
    0.79
    to
    0.66
     postérieures
    0.61
    на
    0.61
    сез
    0.59
    و
    0.59
     postérieure
    0.58
    z
    0.57
    م
    0.57
    POSITIVE LOGITS
     under
    1.13
    neath
    1.03
    under
    1.02
     auspices
    0.96
     purview
    0.90
    Under
    0.81
     guise
    0.78
     unter
    0.77
     bajo
    0.77
     scrutiny
    0.76
    Activations Density 0.032%

    No Known Activations