© 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. 117904
    Prev
    Next
    INDEX
    Explanations

    crimes committed

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

    Vesicles and telomeres

    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
     поступа
    0.58
    者は
    0.55
    ുകയാണ്
    0.51
     ayaa
    0.50
    ườn
    0.50
    成り立つ
    0.50
    자는
    0.49
    猟
    0.49
    の実
    0.49
     фараз
    0.49
    POSITIVE LOGITS
    at
    0.59
     Grounds
    0.49
     Minden
    0.47
     binders
    0.44
     Mind
    0.44
    chan
    0.44
     Life
    0.43
     Release
    0.43
    prim
    0.43
     Fas
    0.43
    Activations Density 0.001%

    No Known Activations