© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13115
    Prev
    Next
    INDEX
    Explanations

    embarrass, humiliate, offend, forget

    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_13_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
     你
    1.72
     は
    1.45
     .....
    1.41
     这是
    1.38
      
    1.36
     除了
    1.35
     虽然
    1.33
     如果
    1.33
    如果你
    1.32
     ....
    1.32
    POSITIVE LOGITS
     solvation
    1.38
    idimensional
    1.37
    ometrical
    1.37
    éssel
    1.36
    bezpie
    1.32
    hydraz
    1.28
    asadd
    1.26
    csim
    1.26
    verläss
    1.26
    carboxylate
    1.26
    Activations Density 0.452%

    No Known Activations