© 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. 20517
    Prev
    Next
    INDEX
    Explanations

    头两句

    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
    鲔
    1.06
    螓
    1.00
    螫
    0.95
    鏻
    0.92
    睪
    0.92
    鳟
    0.89
    齙
    0.89
    楦
    0.89
    銠
    0.86
    嗥
    0.86
    POSITIVE LOGITS
    x
    0.85
    3
    0.83
    1
    0.81
     y
    0.79
    f
    0.78
    5
    0.78
     l
    0.77
    r
    0.76
    2
    0.75
     t
    0.74
    Activations Density 0.001%

    No Known Activations