© 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. 22-GEMMASCOPE-RES-131K
    7. 14738
    Prev
    Next
    INDEX
    Explanations

    calculating distance

    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
     ASSOCIATES
    -1.02
     reddish
    -1.01
    redhat
    -0.98
     pimenta
    -0.96
    ajuste
    -0.93
    peluche
    -0.93
     որ
    -0.90
    tvr
    -0.89
    ventajas
    -0.88
     largura
    -0.88
    POSITIVE LOGITS
     distance
    1.33
    distance
    1.32
    Comparing
    1.16
     Distance
    1.02
    距離
    0.98
     comparing
    0.98
     срав
    0.98
     distanced
    0.98
    距离
    0.98
    Distance
    0.97
    Activations Density 0.011%

    No Known Activations