© 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. 4174
    Prev
    Next
    INDEX
    Explanations

    far apart

    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
    �
    2.40
    ‐
    2.40
    ��
    2.26
    oz
    2.25
    oo
    2.21
     mil
    2.07
    ovski
    2.07
         
    2.05
    mala
    2.03
     rammed
    2.02
    POSITIVE LOGITS
    ]-\
    2.90
     espíritu
    2.86
    LESS
    2.75
    pictureBox
    2.70
     enfoque
    2.69
     محکمہ
    2.67
    \}-
    2.67
    PTION
    2.66
    ToCheck
    2.62
    BURSE
    2.62
    Activations Density 0.148%

    No Known Activations