© 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. 32577
    Prev
    Next
    INDEX
    Explanations

    comprises determining

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

    heart actually stops

    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
    slow
    0.54
     puts
    0.48
    टने
    0.45
    ↵
    0.44
    webp
    0.44
    ovne
    0.44
    חה
    0.43
    offs
    0.42
    range
    0.41
    sass
    0.41
    POSITIVE LOGITS
     solche
    0.54
     diesen
    0.53
    ૩
    0.52
     interfaz
    0.49
     solchen
    0.49
     unseren
    0.48
    导体
    0.47
     εκεί
    0.47
     автоматы
    0.47
     honom
    0.46
    Activations Density 0.000%

    No Known Activations