© 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. 23913
    Prev
    Next
    INDEX
    Explanations

    events unfolding

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

    as x increases

    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
    줘야
    0.50
     хотела
    0.43
    પ
    0.43
     પા
    0.43
    andingan
    0.43
    狷
    0.43
    })$
    0.42
     לב
    0.41
    ﾃ
    0.41
     হেন
    0.41
    POSITIVE LOGITS
     gears
    0.47
     nears
    0.47
     progresses
    0.47
     näher
    0.46
     matures
    0.45
     fos
    0.43
     grows
    0.43
    越来越多的
    0.41
     more
    0.40
     Increasingly
    0.39
    Activations Density 0.055%

    No Known Activations