© 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. 70441
    Prev
    Next
    INDEX
    Explanations

    words from multiple languages

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

    lung volume

    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
     তাহা
    0.45
    o
    0.45
     Wyatt
    0.44
     BYU
    0.43
     Wyoming
    0.42
     Zert
    0.41
     SBOM
    0.41
     Shasta
    0.41
    ".$
    0.40
     journaling
    0.40
    POSITIVE LOGITS
    ussie
    0.50
    ຕິດຕໍ່
    0.46
     Германия
    0.45
     unprecedented
    0.45
     ರಾಷ್ಟ
    0.43
     océ
    0.43
    ੜ
    0.43
     endemic
    0.43
    bukti
    0.43
     Europeo
    0.43
    Activations Density 0.001%

    No Known Activations