© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48391
    Prev
    Next
    INDEX
    Explanations

    subject then verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     variously
    -1.20
     erst
    -1.17
     heretofore
    -1.16
     belated
    -1.13
     Notwithstanding
    -1.10
    Ordin
    -1.06
     environs
    -1.05
     occasioned
    -1.05
     invariably
    -1.03
     надо
    -1.02
    POSITIVE LOGITS
     overall
    1.13
     continuously
    1.10
     heavily
    1.09
     solely
    1.04
     majority
    1.03
     deem
    1.03
    所
    1.03
    Alike
    1.01
    pageY
    1.00
     coined
    0.98
    Activations Density 0.128%

    No Known Activations