© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246673
    Prev
    Next
    INDEX
    Explanations

    assert macro is not intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Penelitian
    0.53
     Trauma
    0.51
     Ảnh
    0.49
    受け
    0.46
     Acá
    0.46
    受賞
    0.45
     Poverty
    0.45
     எடுத்த
    0.45
    胝
    0.45
     Prem
    0.45
    POSITIVE LOGITS
     lids
    0.50
     pptd
    0.49
     posle
    0.46
    vocals
    0.45
     vst
    0.44
     verticales
    0.44
     irgende
    0.44
     umfang
    0.43
     flashes
    0.42
     mnog
    0.42
    Activations Density 0.000%

    No Known Activations