© 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. 16063
    Prev
    Next
    INDEX
    Explanations

    concise writing

    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
    reszt
    0.76
    甚至
    0.70
     shouting
    0.69
    或其他
    0.68
     后
    0.67
    或
    0.65
    碱
    0.64
    eye
    0.64
    昃
    0.64
     eye
    0.63
    POSITIVE LOGITS
     affirm
    0.81
     حاض
    0.77
     Chances
    0.76
     Ranked
    0.75
     endeavours
    0.75
     cuantos
    0.75
     Oft
    0.75
     beinh
    0.75
     beban
    0.74
    ishwa
    0.74
    Activations Density 0.011%

    No Known Activations