© 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. 58294
    Prev
    Next
    INDEX
    Explanations

    negating or reversing actions

    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
     подъ
    -0.90
     отсутствие
    -0.89
     identi
    -0.86
    echt
    -0.86
    是否有
    -0.82
     confer
    -0.82
     essays
    -0.81
     initi
    -0.81
     acc
    -0.80
     legiti
    -0.77
    POSITIVE LOGITS
    iscono
    0.84
     aanzien
    0.80
     bestaande
    0.79
    énération
    0.79
     concealment
    0.78
     மூ
    0.76
    savage
    0.76
     doing
    0.76
     onderwijs
    0.75
    avent
    0.73
    Activations Density 0.019%

    No Known Activations