© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3803
    Prev
    Next
    INDEX
    Explanations

    sense of abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ্ম্ম
    2.96
    یم
    2.66
    ြ
    2.57
    érences
    2.53
    ípios
    2.50
    ił
    2.48
    एफआई
    2.48
    ть
    2.46
    ે
    2.45
    ো
    2.43
    POSITIVE LOGITS
    𝐮
    2.86
    𝐦
    2.79
    𝐨
    2.74
    𝐚
    2.73
    𝐞
    2.73
    𝐧
    2.67
    𝐫
    2.57
    𝐩
    2.55
    𝐢
    2.51
     guiclass
    2.46
    Activations Density 0.025%

    No Known Activations