© 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. 22126
    Prev
    Next
    INDEX
    Explanations

    website hosting

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

    specific units and game mechanics

    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
     அவ்வ
    0.52
     INCIDENTAL
    0.50
     अन्य
    0.50
     иных
    0.48
     discontinuities
    0.46
     ९
    0.44
     注
    0.43
     來
    0.43
     மற்ற
    0.42
     instability
    0.42
    POSITIVE LOGITS
    you
    0.43
     befri
    0.43
    parte
    0.41
     equivale
    0.41
    friends
    0.40
     pampered
    0.40
    dek
    0.39
     geralmente
    0.39
    arlings
    0.39
     velho
    0.39
    Activations Density 0.000%

    No Known Activations