© 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. 30655
    Prev
    Next
    INDEX
    Explanations

    making informed decisions

    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
     résultat
    -1.12
    μένος
    -1.03
    źdz
    -1.01
     résultats
    -0.99
    uſ
    -0.98
     inspec
    -0.96
     vacacionales
    -0.92
     trava
    -0.91
     ſon
    -0.91
    ครื่อง
    -0.91
    POSITIVE LOGITS
     decision
    2.42
     decisions
    2.31
     planning
    2.13
     informed
    1.90
     better
    1.79
     decide
    1.60
     accurate
    1.50
     deciding
    1.46
     inform
    1.45
    decision
    1.42
    Activations Density 0.136%

    No Known Activations