© 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. 72856
    Prev
    Next
    INDEX
    Explanations

    confirmation or negation

    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
     लोगों
    -0.84
    ├──
    -0.83
    riert
    -0.81
     både
    -0.79
    σί
    -0.79
    疫苗
    -0.76
     menuju
    -0.76
     prachtige
    -0.76
     contraband
    -0.75
     administra
    -0.74
    POSITIVE LOGITS
    nop
    0.85
    Confirmation
    0.83
     Confirmation
    0.82
     unaffected
    0.80
     confirmation
    0.77
     ничего
    0.77
     nothing
    0.76
     unimportant
    0.73
     никаких
    0.69
     confirm
    0.69
    Activations Density 0.119%

    No Known Activations