© 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. 64002
    Prev
    Next
    INDEX
    Explanations

    determiner/pronoun followed by action/attribute

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

    to regain competitiveness

    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
     экспери
    0.45
    لاء
    0.43
    電腦
    0.43
    Experiment
    0.43
    =
    0.42
     be
    0.41
     rive
    0.41
     從
    0.40
    Arithmetic
    0.40
    MouseDown
    0.39
    POSITIVE LOGITS
     reimag
    0.55
     relembrar
    0.52
     emojis
    0.48
     tasked
    0.47
     चाहर
    0.46
    ष्‍ट्र
    0.46
     ehemal
    0.45
     agrade
    0.43
     selfies
    0.42
     सेल्फी
    0.42
    Activations Density 0.000%

    No Known Activations