© 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. 31-GEMMASCOPE-2-RES-262K
    7. 21533
    Prev
    Next
    INDEX
    Explanations

    involved in

    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
     后
    0.67
    impose
    0.64
    ’।
    0.63
     for
    0.62
     حتى
    0.59
     want
    0.59
    нике
    0.59
     숨
    0.59
     이유
    0.58
     don
    0.58
    POSITIVE LOGITS
    l
    0.82
    m
    0.81
    g
    0.81
    t
    0.78
    i
    0.78
    ในการ
    0.77
     involved
    0.75
     tradeoffs
    0.74
    ad
    0.74
    व
    0.72
    Activations Density 0.039%

    No Known Activations