© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128790
    Prev
    Next
    INDEX
    Explanations

    condemn, condemnation

    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
    pegno
    -1.91
    殲
    -1.83
    нение
    -1.83
    軋
    -1.83
    hintText
    -1.82
    zembro
    -1.81
     who
    -1.78
    </h3>
    -1.73
     και
    -1.70
     überprü
    -1.70
    POSITIVE LOGITS
    ↵
    3.05
    1
    2.03
    7
    1.96
    9
    1.78
    0
    1.77
    8
    1.77
    zelfde
    1.76
     MULTI
    1.74
    5
    1.73
    6
    1.73
    Activations Density 0.009%

    No Known Activations