© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 190
    Prev
    Next
    INDEX
    Explanations

    как избежать

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

    движение, поднятие

    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_53_width_65k_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
     對
    0.44
    ᅴ
    0.42
     會
    0.40
    ﮈ
    0.40
    dimensioni
    0.39
    larghezza
    0.39
     ainfi
    0.38
    REGIUNE
    0.38
    تھی
    0.38
    نیٹ
    0.38
    POSITIVE LOGITS
     не
    0.57
     по
    0.54
     в
    0.52
     про
    0.52
     во
    0.52
     при
    0.52
     со
    0.52
     на
    0.51
     и
    0.50
     все
    0.50
    Activations Density 0.022%

    No Known Activations