© 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. 70365
    Prev
    Next
    INDEX
    Explanations

    low and high boundary assignments

    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
    煖
    1.31
    ској
    1.20
     пережи
    1.08
    螻
    1.07
    龕
    1.06
     sensação
    1.03
    __":
    1.03
    リューム
    1.02
     зави
    1.00
    瓔
    0.98
    POSITIVE LOGITS
    ad
    2.02
     ads
    1.98
     Old
    1.97
     optomet
    1.95
    acy
    1.95
     Astronomy
    1.94
    arch
    1.92
     Antenna
    1.89
     aliens
    1.88
     TFT
    1.88
    Activations Density 0.000%

    No Known Activations