© 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. 84191
    Prev
    Next
    INDEX
    Explanations

    priced securities

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

    character description prompts

    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
    だけど
    0.49
    しくて
    0.48
    らず
    0.47
     ด่า
    0.47
    7
    0.46
     Miloš
    0.46
    又は
    0.45
     자세
    0.44
     있다면
    0.44
     ያ
    0.44
    POSITIVE LOGITS
     subtle
    0.47
     anaer
    0.45
     carvings
    0.44
     enzym
    0.43
     brillante
    0.43
     bioge
    0.42
     magní
    0.42
     stained
    0.42
     inev
    0.42
     opera
    0.42
    Activations Density 0.003%

    No Known Activations