© 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-16K
    7. 10138
    Prev
    Next
    INDEX
    Explanations

    years in the 1970s

    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
     Instagram
    1.25
     hashtag
    1.08
     Airbnb
    1.07
    ﻑ
    1.07
     Assad
    1.04
    wu
    1.03
     Gatsby
    1.02
     Vimeo
    0.99
     influencer
    0.99
    Instagram
    0.98
    POSITIVE LOGITS
     cread
    1.01
    о
    1.00
     brengen
    0.99
     str
    0.91
    悌
    0.88
    ┼
    0.85
    ia
    0.84
    ᚄ
    0.84
    ид
    0.84
     fragen
    0.84
    Activations Density 0.018%

    No Known Activations