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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 91
    Prev
    Next
    INDEX
    Explanations

    generating `here`

    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
    lar
    0.59
    s
    0.54
    …
    0.52
     trivia
    0.50
      
    0.50
    link
    0.49
    궁
    0.49
    叫
    0.49
    ിക്കുന്നത്
    0.49
    ...
    0.49
    POSITIVE LOGITS
     Here
    1.46
     aquí
    1.39
     here
    1.35
     Aquí
    1.31
     HERE
    1.24
     Berikut
    1.22
     aqui
    1.22
    Here
    1.18
    以下
    1.16
     Below
    1.15
    Activations Density 1.379%

    No Known Activations