© 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. 10-GEMMASCOPE-RES-131K
    7. 38654
    Prev
    Next
    INDEX
    Explanations

    numbers like 33, 3, 333, 33.33%

    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_10/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
     melap
    -1.82
     who
    -1.66
    𖥧
    -1.56
     related
    -1.52
     figlio
    -1.49
    </em>
    -1.48
    ꦱ
    -1.48
     القوات
    -1.45
    られない
    -1.44
    那我
    -1.44
    POSITIVE LOGITS
     "
    2.17
    }
    1.80
     besonder
    1.70
    </h1>
    1.56
    kaç
    1.55
    篌
    1.50
     "'
    1.49
    ⁺
    1.48
    carte
    1.48
     菇
    1.47
    Activations Density 0.004%

    No Known Activations