© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76620
    Prev
    Next
    INDEX
    Explanations

    medical and descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite

    medical and technical analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    וק
    0.61
    ानिस्तान
    0.52
    兟
    0.52
    δικ
    0.50
    㶱
    0.47
     банков
    0.47
    律师
    0.47
     barrister
    0.47
    ित
    0.46
    㷅
    0.46
    POSITIVE LOGITS
     spectrophot
    0.65
     excreted
    0.65
     costo
    0.58
     physiologically
    0.54
     clinically
    0.54
     satiety
    0.53
     evaluated
    0.53
    Treatment
    0.53
     physiologic
    0.53
     preventive
    0.52
    Activations Density 0.000%

    No Known Activations