© 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. 127568
    Prev
    Next
    INDEX
    Explanations

    previous button or code

    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
    ↵↵
    -3.61
    }
    -2.73
    </strong>
    -2.73
    -2.42
     vroeger
    -2.42
     We
    -2.38
    𖥧
    -2.38
     …”
    -2.38
    ,’
    -2.34
    “
    -2.34
    POSITIVE LOGITS
    鯢
    3.00
     étrang
    2.92
    ꪹ
    2.86
    嗆
    2.67
     prenota
    2.66
     sconto
    2.64
    ᯅ
    2.63
    躋
    2.61
    车的
    2.59
    蕷
    2.59
    Activations Density 0.001%
    No Known Activations