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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1874
    Prev
    Next
    INDEX
    Explanations

    will tell or disclose

    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
     ನೋಡ
    0.95
    achta
    0.86
     చూడ
    0.85
    堛
    0.81
     பார்த்த
    0.79
     рассматри
    0.79
    卷积
    0.78
     دیکھتے
    0.78
    惋
    0.77
     melihat
    0.77
    POSITIVE LOGITS
     disclose
    2.18
     disclosing
    2.10
     disclosure
    2.04
     disclosures
    1.98
     divulge
    1.95
     disclosed
    1.94
     divul
    1.87
     discloses
    1.79
     Disclosure
    1.79
    disclosure
    1.78
    Activations Density 0.995%

    No Known Activations