© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2868
    Prev
    Next
    INDEX
    Explanations

    assumptions

    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
    Negative Logits
    ]})
    3.16
    ル
    3.02
    ే
    3.01
    ন
    2.90
    ist
    2.80
    mentation
    2.80
    te
    2.73
    ן
    2.72
    GeV
    2.66
    й
    2.65
    POSITIVE LOGITS
    寐
    3.30
    ح
    3.21
    я
    3.08
     Szen
    3.04
    𝐬
    2.97
    𝐧
    2.95
    𝐢
    2.79
    ை
    2.78
    ঞ্চলিক
    2.74
    𝐥
    2.73
    Activations Density 0.373%

    No Known Activations