© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92877
    Prev
    Next
    INDEX
    Explanations

    passages, straits, and canals

    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
    chase
    -0.75
     пружи
    -0.74
    vens
    -0.74
     bamboo
    -0.73
     dieser
    -0.73
     รับ
    -0.73
    vanja
    -0.73
    Forest
    -0.72
     PARK
    -0.72
     séries
    -0.71
    POSITIVE LOGITS
     passage
    1.38
     Suez
    1.35
    passage
    1.27
     Passage
    1.25
    shipping
    1.21
     shipping
    1.21
     straits
    1.21
    Passage
    1.20
     Straits
    1.17
     Strait
    1.12
    Activations Density 0.028%

    No Known Activations