© 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-16K
    4. 10471
    Prev
    Next
    INDEX
    Explanations

    even experienced

    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
     barely
    1.07
    ifiably
    1.05
     really
    0.99
    really
    0.94
     casually
    0.93
     miserably
    0.88
     modestly
    0.88
    🧉
    0.86
     downright
    0.85
     impatiently
    0.84
    POSITIVE LOGITS
     inoltre
    0.93
    다는
    0.88
    即使
    0.84
    正しい
    0.81
    Substitution
    0.81
     Ensuite
    0.79
     повинні
    0.79
     Однако
    0.79
    Addition
    0.79
    原因
    0.78
    Activations Density 0.022%

    No Known Activations