© 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. 79025
    Prev
    Next
    INDEX
    Explanations

    leprechaun hat

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

    lists, descriptions of specific items

    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
    ając
    0.53
     colorChoice
    0.52
    ндекс
    0.48
    ającej
    0.47
    findContacts
    0.46
    ających
    0.46
    㑒
    0.46
     அன்ற
    0.45
    tpVar
    0.45
     усіх
    0.44
    POSITIVE LOGITS
     mág
    0.47
    6
    0.45
    7
    0.43
     divertido
    0.43
     by
    0.43
     Please
    0.43
     ermöglicht
    0.42
     umož
    0.42
    -
    0.42
    z
    0.42
    Activations Density 0.000%

    No Known Activations