© 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. 16337
    Prev
    Next
    INDEX
    Explanations

    setting questions

    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
     can
    0.73
     Replacing
    0.72
     a
    0.71
     sexually
    0.71
     about
    0.70
     replacing
    0.70
     {
    0.70
    很
    0.69
     not
    0.69
     incorrect
    0.69
    POSITIVE LOGITS
     Essays
    1.17
    Essay
    1.08
     essay
    1.04
     Essay
    1.01
    université
    0.98
     essays
    0.93
    essay
    0.90
     phd
    0.89
    槅
    0.89
    㢳
    0.89
    Activations Density 0.001%

    No Known Activations