© 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. 103507
    Prev
    Next
    INDEX
    Explanations

    reporting terminated pregnancies

    np_acts-logits-general · gemini-2.5-flash-lite

    database fields and labels

    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
     배워
    0.44
    (),
    0.42
    :=
    0.41
     tackling
    0.41
    க்கமாக
    0.41
     méthodes
    0.41
     экономики
    0.40
    invoke
    0.39
    बाजी
    0.38
    у
    0.38
    POSITIVE LOGITS
     They
    0.44
     antigüedad
    0.44
     ikke
    0.43
    ottesville
    0.42
     Colton
    0.41
     adjustable
    0.41
     Kauai
    0.41
     niet
    0.40
     forêt
    0.40
     nicht
    0.40
    Activations Density 0.005%

    No Known Activations