© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81258
    Prev
    Next
    INDEX
    Explanations

    doing/was/were + action/state

    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
     parfois
    -1.10
    veranstal
    -1.08
    sometimes
    -1.08
    aritions
    -1.05
    ידה
    -1.04
    often
    -1.03
     Gläub
    -1.02
     souvent
    -1.01
     mindig
    -1.01
    always
    -1.00
    POSITIVE LOGITS
    百姓
    1.22
     had
    1.09
     probably
    0.99
     household
    0.98
     evidently
    0.95
     wahrscheinlich
    0.94
     presumably
    0.94
    匠
    0.92
    --*/
    0.90
    ="[
    0.88
    Activations Density 0.023%

    No Known Activations