© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62396
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and states

    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
    Negative Logits
    LING
    -0.91
    というのが
    -0.88
    ZZO
    -0.88
     Babi
    -0.88
    鑁
    -0.86
    μφ
    -0.85
     wald
    -0.84
     packers
    -0.84
     meto
    -0.83
     refroidissement
    -0.83
    POSITIVE LOGITS
     in
    1.24
     during
    1.12
     dimensions
    1.10
    dalam
    1.04
     beliefs
    1.04
    related
    1.02
     dimension
    0.99
     styles
    0.96
     scores
    0.96
     orientation
    0.94
    Activations Density 0.282%

    No Known Activations