© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1416
    Prev
    Next
    INDEX
    Explanations

    ready when or ready to

    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_17_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
    el
    1.63
    ために
    1.56
    но
    1.53
    ֡
    1.48
    ed
    1.40
     $$\
    1.38
    劑
    1.36
    琹
    1.35
    ique
    1.34
    तावनी
    1.33
    POSITIVE LOGITS
     कराए
    1.90
    icii
    1.54
     tràn
    1.44
     foragers
    1.43
    NESS
    1.42
    forEach
    1.41
     jiv
    1.40
    żą
    1.40
     smashing
    1.40
    ineri
    1.39
    Activations Density 0.249%

    No Known Activations