© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9894
    Prev
    Next
    INDEX
    Explanations

    list structure and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
    Implementation
    0.76
    نىڭ
    0.75
    Requirements
    0.74
    پ
    0.73
    ޕ
    0.72
    dimensions
    0.71
    Dimensions
    0.71
    Potential
    0.71
    netHex
    0.71
    Requirement
    0.70
    POSITIVE LOGITS
     김
    1.47
     사
    1.42
     kimchi
    1.42
     서
    1.39
     장
    1.38
     비
    1.36
     메
    1.36
     포
    1.34
     정보
    1.34
     시
    1.32
    Activations Density 0.024%

    No Known Activations