© 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. 49119
    Prev
    Next
    INDEX
    Explanations

    Explain, describe, discuss, state

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

    asking for explanations or definitions

    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
    ভূমিতে
    0.42
     rented
    0.40
     renting
    0.38
    атра
    0.38
     vuông
    0.36
    χος
    0.36
    /")
    0.36
    ამდე
    0.36
     eels
    0.36
     {})
    0.35
    POSITIVE LOGITS
    重视
    0.44
    Eddie
    0.43
    Why
    0.41
     why
    0.41
    Describe
    0.40
    Explain
    0.40
    Theorem
    0.39
     connaître
    0.39
    Ted
    0.39
     dwie
    0.38
    Activations Density 0.004%

    No Known Activations