© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 105674
    Prev
    Next
    INDEX
    Explanations

    speaking about years

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

    an Revolution (2014)

    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
    匀
    0.49
     miraculously
    0.44
    --
    0.42
    ピ
    0.41
     із
    0.39
     remedy
    0.39
     anyway
    0.38
     signed
    0.38
     presso
    0.38
     sufficiency
    0.38
    POSITIVE LOGITS
     Geschäft
    0.51
     előtt
    0.51
     unabhäng
    0.50
     Eigent
    0.49
    ெடு
    0.48
    濰
    0.48
     gyárt
    0.48
     Sartre
    0.48
     Eink
    0.48
     Persön
    0.47
    Activations Density 0.000%

    No Known Activations