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. 3696
    Prev
    Next
    INDEX
    Explanations

    "I cannot and will not"

    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
     been
    1.50
    $)$.
    1.33
     быть
    1.29
    вать
    1.28
    ない
    1.26
    been
    1.25
    -\
    1.24
    नी
    1.15
    ۥ
    1.11
    enting
    1.11
    POSITIVE LOGITS
    oughby
    1.91
     sicuramente
    1.91
    amette
    1.80
    ows
    1.58
    িয়াম
    1.56
     gladly
    1.54
    kommen
    1.52
     certamente
    1.51
    িয়াম
    1.45
     şekilde
    1.40
    Activations Density 0.116%

    No Known Activations