© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86910
    Prev
    Next
    INDEX
    Explanations

    inertia and inertial concepts

    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
    配合
    -0.73
    bites
    -0.73
     Columbus
    -0.73
     Tourismus
    -0.71
     glued
    -0.71
    Columbus
    -0.71
    ické
    -0.68
    阕
    -0.67
     Alber
    -0.67
     bombardment
    -0.67
    POSITIVE LOGITS
     Poitiers
    0.70
    beutel
    0.68
     radix
    0.67
    覧
    0.66
    vlog
    0.66
    頂
    0.65
    Holland
    0.65
     dreamer
    0.65
     Jewell
    0.65
     loài
    0.64
    Activations Density 0.085%

    No Known Activations