© 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. 50999
    Prev
    Next
    INDEX
    Explanations

    "a" or "the" followed by concept

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

    AI synthesizing information

    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
     unclaimed
    0.52
     உரிய
    0.47
     جلوگیری
    0.47
     disertai
    0.47
     {}'.
    0.46
    ḍ
    0.46
     alleges
    0.45
     testifies
    0.45
    য্
    0.45
    dostęp
    0.45
    POSITIVE LOGITS
    פ
    0.50
    ט
    0.49
     பாம்பு
    0.46
    ק
    0.45
     keyboard
    0.44
    ق
    0.44
     spoons
    0.44
    น
    0.44
     caméra
    0.44
     lenguaje
    0.43
    Activations Density 0.000%

    No Known Activations