© 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. 116513
    Prev
    Next
    INDEX
    Explanations

    India, China, hold, itty bitty

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

    team, problem, race

    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
    ন
    0.55
    юнча
    0.50
    количество
    0.47
     একেবারে
    0.46
    न
    0.46
     подойдет
    0.46
     дал
    0.45
    ңыз
    0.45
     позволит
    0.45
     молодо
    0.44
    POSITIVE LOGITS
    (/(
    0.47
     fakult
    0.46
     DateTime
    0.44
     merak
    0.44
     "/"
    0.44
    PIRE
    0.44
     dia
    0.43
     DFT
    0.42
     Utama
    0.42
     servent
    0.42
    Activations Density 0.007%

    No Known Activations