© 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. 71821
    Prev
    Next
    INDEX
    Explanations

    incentive and incentives

    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
    、“
    -1.98
    これまで
    -1.86
    お知らせ
    -1.84
     interestingly
    -1.81
    写真は
    -1.80
     multitude
    -1.79
     we
    -1.79
     coveted
    -1.77
    〝
    -1.75
    レトロ
    -1.70
    POSITIVE LOGITS
     Beispiel
    1.77
     reward
    1.64
    errHandler
    1.63
    gefügt
    1.61
    ござ
    1.59
     worlds
    1.58
    朥
    1.54
     odkazy
    1.53
    ченным
    1.53
    られた
    1.52
    Activations Density 0.009%

    No Known Activations