© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69336
    Prev
    Next
    INDEX
    Explanations

    I/O Performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     listop
    2.03
     chup
    1.96
     fotografía
    1.89
    喺
    1.87
     caminar
    1.86
    攝
    1.84
     LikeLike
    1.82
     micró
    1.80
     Harare
    1.79
     enteros
    1.78
    POSITIVE LOGITS
     VIII
    1.06
     IX
    0.90
    o
    0.89
    O
    0.86
     Carte
    0.81
    asm
    0.80
    matu
    0.80
     Vaz
    0.80
     computation
    0.80
     Lig
    0.79
    Activations Density 0.001%

    No Known Activations