© 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. 3969
    Prev
    Next
    INDEX
    Explanations

    eval()

    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
    Negative Logits
    Texto
    2.00
     小型
    1.97
     然而
    1.97
     初始化
    1.90
     例如
    1.87
     Τα
    1.87
    例
    1.86
     نحو
    1.85
     SignIn
    1.80
    𒁹
    1.78
    POSITIVE LOGITS
    usses
    1.45
    iffent
    1.20
    iest
    1.20
     concurrence
    1.16
    isr
    1.15
     bleeding
    1.15
     nearest
    1.13
     bit
    1.13
    ussians
    1.12
     portion
    1.09
    Activations Density 0.000%

    No Known Activations