© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72397
    Prev
    Next
    INDEX
    Explanations

    Blac Chyna placenta

    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
     now
    -1.18
     for
    -1.17
     this
    -1.15
     these
    -1.13
     from
    -1.09
     many
    -1.09
     most
    -1.08
     stylish
    -1.07
     invigor
    -1.05
     which
    -1.02
    POSITIVE LOGITS
     bénéfices
    1.08
     отсут
    1.06
    ダウンロード
    1.01
    えっ
    1.01
     indiquer
    0.99
     accompagner
    0.99
    訁
    0.98
     éviter
    0.97
    瘣
    0.97
     premières
    0.96
    Activations Density 0.000%

    No Known Activations