© 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. 30474
    Prev
    Next
    INDEX
    Explanations

    adding cost

    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
    Helps
    -0.85
     damaging
    -0.84
    Helping
    -0.83
    ∂
    -0.79
    ticle
    -0.78
     harmful
    -0.77
    includes
    -0.77
    allows
    -0.76
    issage
    -0.76
     Wandel
    -0.75
    POSITIVE LOGITS
     adds
    3.06
     adding
    2.69
     add
    2.45
    增加
    2.42
     Adds
    2.38
     added
    2.27
     slows
    2.27
    adds
    2.22
     Adding
    2.20
     добавля
    2.16
    Activations Density 0.105%

    No Known Activations