© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 689
    Prev
    Next
    INDEX
    Explanations

    Write a story

    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_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
     있던
    1.01
    층
    0.99
     mesta
    0.94
    后的
    0.94
     보이는
    0.93
     남아
    0.93
     후
    0.92
     ganz
    0.91
    곳
    0.90
    듯
    0.89
    POSITIVE LOGITS
     dyslexia
    0.97
     earnestly
    0.96
     datt
    0.96
     reminiscent
    0.95
     AVLNode
    0.95
    brack
    0.94
     nicknamed
    0.94
     vicious
    0.93
     moths
    0.93
     varsity
    0.93
    Activations Density 0.001%

    No Known Activations