© 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. 21089
    Prev
    Next
    INDEX
    Explanations

    multilingual modal verbs

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

    also, capable, and funeral

    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
     작
    0.41
     ставак
    0.39
    他和
    0.39
     বিজ্ঞানী
    0.39
    🦂
    0.38
     Greenberg
    0.38
     Karriere
    0.38
     ],"
    0.38
    古
    0.37
     لدى
    0.36
    POSITIVE LOGITS
     देखील
    0.51
     també
    0.44
     również
    0.44
     menjal
    0.44
    нена
    0.43
     puedan
    0.43
     могли
    0.43
    邡
    0.43
     inescapable
    0.42
     possa
    0.42
    Activations Density 0.000%

    No Known Activations