© 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. 32446
    Prev
    Next
    INDEX
    Explanations

    install the

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

    cell references

    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
    年間
    0.50
    apper
    0.47
     também
    0.46
     zakup
    0.45
     frá
    0.44
    調
    0.44
    miktar
    0.44
     navide
    0.43
     nejen
    0.43
     избежать
    0.43
    POSITIVE LOGITS
    рие
    0.48
    迎来
    0.43
    ScienceStudent
    0.40
     열심히
    0.39
     selectivity
    0.38
    ynitrite
    0.38
    股价
    0.38
    ᕐ
    0.37
    లోకి
    0.37
    更容易
    0.37
    Activations Density 0.000%

    No Known Activations