Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9121
    Prev
    Next
    INDEX
    Explanations

    state rankings

    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
     Tensorflow
    0.81
     Atari
    0.79
     SoundCloud
    0.75
     Folklore
    0.75
    ศิลป
    0.74
     Biografie
    0.74
     तेरी
    0.73
    ლ
    0.72
     theoretical
    0.70
     artist
    0.69
    POSITIVE LOGITS
     rankings
    1.73
     ranking
    1.58
     Rankings
    1.55
    ranking
    1.44
     рейтинг
    1.43
     ratings
    1.41
     рейти
    1.39
     рейтин
    1.34
     ranked
    1.33
     Ratings
    1.30
    Activations Density 0.470%

    No Known Activations