© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2396
    Prev
    Next
    INDEX
    Explanations

    state of becoming

    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_9_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
    
    1.53
    鸯
    1.52
    er
    1.50
    p
    1.48
    ︎
    1.45
    peng
    1.42
    pä
    1.41
    heba
    1.40
    ounds
    1.39
    произ
    1.38
    POSITIVE LOGITS
    𝐫
    1.87
    توان
    1.86
     irreparable
    1.65
    ও
    1.64
     synonymous
    1.60
    ्ज
    1.60
     overseeing
    1.59
    ય
    1.57
     बैठे
    1.56
    ia
    1.51
    Activations Density 0.079%

    No Known Activations