© 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. 66093
    Prev
    Next
    INDEX
    Explanations

    interdependence and extrapolation

    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
     enlever
    -0.77
    IAM
    -0.75
    endent
    -0.75
     vklju
    -0.74
     циф
    -0.74
     itself
    -0.73
    ポイントは
    -0.73
    ires
    -0.73
     договора
    -0.73
    PerSecond
    -0.71
    POSITIVE LOGITS
     each
    1.11
     взаимо
    1.09
     one
    1.06
    互相
    1.00
     shared
    0.92
     interdependence
    0.91
     interdependent
    0.90
    Each
    0.90
     transfer
    0.86
    共通
    0.85
    Activations Density 0.151%

    No Known Activations