© 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. 150517
    Prev
    Next
    INDEX
    Explanations

    purpose and description

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

    seeking practical, in building, delve into

    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
    Pokémon
    0.50
    starcore
    0.50
     প্রাণ
    0.47
     বাঁচ
    0.46
    တွေကို
    0.46
    Pokemon
    0.45
     የመጀመሪያ
    0.44
    薨
    0.44
     রয়ে
    0.43
     डेंटल
    0.43
    POSITIVE LOGITS
     height
    0.52
     charts
    0.50
     innovator
    0.50
     gelar
    0.49
     siblings
    0.48
     heights
    0.47
     compress
    0.47
     directive
    0.47
     ducts
    0.47
     coda
    0.47
    Activations Density 0.000%

    No Known Activations