© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15242
    Prev
    Next
    INDEX
    Explanations

    bothsame vs pluralright vs leftlinear inequalityshared common identityglow stickssimple words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    G
    0.79
    澳门
    0.76
    转换
    0.76
    F
    0.74
    即
    0.73
    XX
    0.73
    希
    0.72
    改革
    0.72
    创新
    0.70
    ிறு
    0.70
    POSITIVE LOGITS
     both
    1.08
     sowohl
    1.03
     både
    1.01
     DEJ
    0.97
     everything
    0.96
     BoxDecoration
    0.94
    both
    0.93
     BOTH
    0.92
     equipment
    0.90
    bodyA
    0.89
    Activations Density 0.183%

    No Known Activations