© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110692
    Prev
    Next
    INDEX
    Explanations

    ionization or code path

    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
     sbag
    -0.82
    Jones
    -0.81
    Yn
    -0.75
    lakukan
    -0.75
     flera
    -0.73
     のか
    -0.71
    îné
    -0.71
    OffsetY
    -0.71
    IZED
    -0.70
    axial
    -0.69
    POSITIVE LOGITS
     first
    0.81
     add
    0.76
     яко
    0.73
     best
    0.72
     Add
    0.71
     Single
    0.68
    телни
    0.67
     पहले
    0.66
     redistribution
    0.66
     indignation
    0.66
    Activations Density 0.052%

    No Known Activations