© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126026
    Prev
    Next
    INDEX
    Explanations

    medical conditions or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    GCP commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tokyo
    0.51
    בד
    0.50
    ბ
    0.50
    Кли
    0.48
    ibley
    0.47
    baru
    0.46
    מ
    0.46
    Б
    0.46
    Battery
    0.46
    Awards
    0.45
    POSITIVE LOGITS
     desemb
    0.50
     argued
    0.50
     trastornos
    0.49
     don
    0.49
     NSError
    0.49
     threatening
    0.48
     buffering
    0.48
     satir
    0.47
     التحكم
    0.47
     alleviating
    0.47
    Activations Density 0.000%

    No Known Activations