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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14376
    Prev
    Next
    INDEX
    Explanations

    delaware, delays, deliberate

    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
    y
    1.00
    en
    0.99
     havoc
    0.97
    gunaan
    0.96
     tipping
    0.95
     spatula
    0.94
     drastic
    0.93
     turnaround
    0.92
    faster
    0.92
    𝙢
    0.91
    POSITIVE LOGITS
    icato
    1.18
    ()=>{
    1.06
     mismo
    1.06
    anterior
    1.04
    发展
    1.02
     alimento
    1.01
    veloped
    1.01
     Rồi
    1.01
    ights
    1.00
     conscient
    1.00
    Activations Density 0.019%

    No Known Activations