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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53662
    Prev
    Next
    INDEX
    Explanations

    bacteria and biofilms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
     Lawyers
    0.52
     j
    0.47
     Zoology
    0.46
     Clearance
    0.46
     filings
    0.45
    اکی
    0.45
     অফিসে
    0.44
     اعتبار
    0.44
     Corpus
    0.43
     Zwei
    0.40
    POSITIVE LOGITS
     virulence
    0.57
     aminoglycos
    0.52
     бактери
    0.50
     bacter
    0.48
    莢
    0.47
     bacterial
    0.45
     kanamycin
    0.43
     gentamicin
    0.43
     resusc
    0.43
     bacterium
    0.42
    Activations Density 0.036%

    No Known Activations