© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1461
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    òng
    0.66
    ανο
    0.65
     пой
    0.64
    舆
    0.63
    匿名
    0.63
    TNF
    0.60
    documentclass
    0.60
    蜿
    0.59
    omorph
    0.58
    घाडी
    0.58
    POSITIVE LOGITS
     skills
    4.86
     skill
    4.49
     Skills
    4.48
    skills
    4.28
    Skills
    4.21
    Skill
    3.95
     Skill
    3.94
    skill
    3.90
    技能
    3.71
     habilidades
    3.53
    Activations Density 0.909%

    No Known Activations