© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32974
    Prev
    Next
    INDEX
    Explanations

    descriptive terms and their consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     goud
    -0.91
     adatt
    -0.91
    łów
    -0.90
    驩
    -0.90
     đừng
    -0.90
    Теперь
    -0.89
    Arbeit
    -0.89
     eene
    -0.87
    を感じ
    -0.87
     animali
    -0.87
    POSITIVE LOGITS
     out
    0.97
     कोशिश
    0.87
     such
    0.86
     whose
    0.82
     that
    0.81
     testimonials
    0.80
     its
    0.79
     szyb
    0.78
     who
    0.77
     exist
    0.77
    Activations Density 0.109%

    No Known Activations