© 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-262K
    7. 15100
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

    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
    Atlas
    0.81
    Opera
    0.74
     $^{\
    0.73
    Podcast
    0.72
    podcast
    0.71
    Follow
    0.71
     Podcast
    0.70
    リル
    0.70
    Maps
    0.69
     कों
    0.69
    POSITIVE LOGITS
     న
    0.59
     soldi
    0.59
     शार
    0.54
     ਇ
    0.54
    esistenza
    0.53
     বদলে
    0.53
    痩
    0.53
    螳
    0.52
     Bein
    0.52
     safegu
    0.52
    Activations Density 0.004%

    No Known Activations