© 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. 87175
    Prev
    Next
    INDEX
    Explanations

    special brand names

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

    lists, key points, or details

    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
    ništva
    0.58
     स्वाद
    0.56
     शास्त्री
    0.55
    ୦
    0.54
     छत्तीस
    0.53
     тях
    0.53
     obligado
    0.52
     него
    0.51
    ங்களையும்
    0.51
    iguë
    0.51
    POSITIVE LOGITS
     ASH
    0.43
     ASC
    0.43
    Special
    0.42
     Special
    0.42
     BASIS
    0.41
     special
    0.40
    ()):
    0.40
     just
    0.40
    you
    0.40
     performer
    0.40
    Activations Density 0.000%

    No Known Activations