© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8400
    Prev
    Next
    INDEX
    Explanations

    arranging, placing, cutting items

    np_acts-logits-general · gemini-2.5-flash-lite

    placed on top of each other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    窜
    0.45
     شدت
    0.42
    °
    0.40
    ленность
    0.40
    が付
    0.40
    取付
    0.37
    忽然
    0.37
    附
    0.37
    હુ
    0.36
    溃
    0.36
    POSITIVE LOGITS
     upside
    1.08
     lengthwise
    0.77
     carefully
    0.77
     flat
    0.74
     horizontally
    0.73
     inverted
    0.71
     vertically
    0.71
     sideways
    0.69
     Carefully
    0.69
     FLAT
    0.68
    Activations Density 0.143%

    No Known Activations