© 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. 44016
    Prev
    Next
    INDEX
    Explanations

    number of pages

    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
    爣
    0.42
    ppery
    0.41
     일어나
    0.41
     котором
    0.39
    toire
    0.39
     neutralization
    0.38
    дав
    0.38
     לפני
    0.38
     prohibited
    0.38
     పొంద
    0.38
    POSITIVE LOGITS
     Sade
    0.45
    us
    0.42
    u
    0.42
     cartoons
    0.41
     rows
    0.41
    j
    0.41
     arus
    0.40
     spiral
    0.40
     gió
    0.40
    is
    0.39
    Activations Density 0.003%

    No Known Activations