© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76685
    Prev
    Next
    INDEX
    Explanations

    doing actions and their outcomes

    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
    เลข
    -1.00
    🧌
    -0.95
    ailles
    -0.95
    參考文獻
    -0.95
    zęd
    -0.90
    <bos>
    -0.90
    Libert
    -0.89
     konkuren
    -0.89
     blessé
    -0.89
     obrazu
    -0.87
    POSITIVE LOGITS
     everything
    1.24
    everything
    1.12
     so
    1.11
     what
    1.08
    Everything
    1.07
     Everything
    0.95
     away
    0.91
     battle
    0.90
    Whatever
    0.89
     nothing
    0.85
    Activations Density 0.045%

    No Known Activations