© 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. 29-GEMMASCOPE-2-RES-262K
    7. 149867
    Prev
    Next
    INDEX
    Explanations

    pressed

    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_29_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
    ćen
    0.76
    钥
    0.76
     Serialize
    0.76
     आजाद
    0.75
    যা
    0.75
    লেম
    0.74
    Switcher
    0.73
    শৃঙ্খলা
    0.73
     রহমান
    0.73
     এক্সচে
    0.72
    POSITIVE LOGITS
     ward
    0.66
     cis
    0.61
     city
    0.60
     sí
    0.59
    際
    0.59
     πί
    0.59
     inspiration
    0.58
     mayor
    0.57
     fund
    0.57
    帰り
    0.55
    Activations Density 0.001%

    No Known Activations