© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7627
    Prev
    Next
    INDEX
    Explanations

    pseudocyst

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
    ఇ
    0.86
    ἑ
    0.85
    ⸜
    0.83
    鐨
    0.81
     えっと
    0.81
     ತಿಳ
    0.81
    ভাই
    0.80
     amea
    0.79
     よく
    0.79
    ைக்
    0.79
    POSITIVE LOGITS
    P
    1.31
     P
    1.11
    Ph
    1.05
    Probability
    1.05
    Price
    1.04
    Property
    1.01
    Political
    1.00
    Peter
    1.00
    Pressure
    0.99
     Probability
    0.99
    Activations Density 1.003%

    No Known Activations