© 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. 22-GEMMASCOPE-RES-131K
    7. 129058
    Prev
    Next
    INDEX
    Explanations

    action then negative outcome

    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_22/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
     erstmals
    -1.24
    ÑOS
    -1.13
     propone
    -1.05
    迫力
    -1.02
     nawet
    -1.02
     already
    -1.02
     overdue
    -1.00
    Already
    -0.99
     đã
    -0.99
    ociação
    -0.99
    POSITIVE LOGITS
     afterwards
    1.33
     it
    1.27
    послед
    1.17
     thereafter
    1.17
     later
    1.16
     vervolgens
    1.13
     they
    1.09
     subsequently
    1.09
     потім
    1.07
     altrett
    1.02
    Activations Density 0.044%

    No Known Activations