© 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. 30957
    Prev
    Next
    INDEX
    Explanations

    proofreading and editing

    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
     fianco
    -0.79
     authored
    -0.79
     innehåller
    -0.78
    cieux
    -0.77
    亞洲
    -0.77
     tatsäch
    -0.74
     읽
    -0.74
    ゆっくり
    -0.73
    blogspot
    -0.73
     ничего
    -0.73
    POSITIVE LOGITS
     proof
    1.27
    Proof
    1.20
    校
    1.18
     Proof
    1.16
     editing
    1.07
    proof
    1.04
     校
    1.01
    proofing
    0.99
     kelle
    0.90
     checkers
    0.90
    Activations Density 0.040%

    No Known Activations