© 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. 180970
    Prev
    Next
    INDEX
    Explanations

    ads, politics, report

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

    correlation and medical terms

    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
    г
    0.64
    р
    0.57
    ж
    0.55
    토
    0.50
    н
    0.50
    т
    0.50
    Д
    0.50
    фе
    0.49
    ת
    0.49
    ג
    0.49
    POSITIVE LOGITS
     এবং
    0.50
     streptomycin
    0.48
     pediatric
    0.48
     midwifery
    0.47
     Pediatric
    0.47
     scavenging
    0.46
     eosin
    0.46
     flavonoid
    0.46
     outpatient
    0.46
     chromatographic
    0.46
    Activations Density 0.001%

    No Known Activations