© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6
    Prev
    Next
    INDEX
    Explanations

    conjunctions or sentence starters

    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
    Ш
    0.42
    <
    0.41
    ↵↵
    0.40
    four
    0.39
    ..
    0.39
    с
    0.39
    three
    0.39
    Ко
    0.38
    ↵↵↵
    0.38
    under
    0.38
    POSITIVE LOGITS
     Therefore
    0.65
     therefore
    0.58
     therefor
    0.56
     Consequently
    0.55
     However
    0.55
     எனவே
    0.52
     Also
    0.52
     Thankfully
    0.51
     Ancak
    0.51
     하지만
    0.51
    Activations Density 4.994%

    No Known Activations