© 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. 34-GEMMASCOPE-RES-131K
    7. 30255
    Prev
    Next
    INDEX
    Explanations

    numerical data values

    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_34/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
     אחת
    -0.86
    βα
    -0.86
     Ανακτήθηκε
    -0.82
    ска
    -0.80
    üben
    -0.78
     various
    -0.78
    🧺
    -0.77
    ână
    -0.75
    tulo
    -0.74
     vuelven
    -0.74
    POSITIVE LOGITS
     вое
    0.78
     neither
    0.74
     Popp
    0.73
    ]!='
    0.73
    めちゃ
    0.72
     etwa
    0.72
    qb
    0.71
    branded
    0.71
     lisää
    0.71
    Plates
    0.71
    Activations Density 0.016%

    No Known Activations