© 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. 14284
    Prev
    Next
    INDEX
    Explanations

    Sternberg's comments

    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
    τικών
    -1.13
     rigue
    -1.10
     וש
    -1.05
     чехол
    -1.04
     schuhe
    -1.04
     SCIENCES
    -1.02
    的情況
    -1.01
     Unii
    -1.01
    всем
    -1.00
    一闪
    -1.00
    POSITIVE LOGITS
     even
    1.13
     so
    1.09
    四大
    1.06
     thinks
    0.95
     distintas
    0.92
    基金
    0.91
    必定
    0.91
    五大
    0.91
     quicker
    0.90
     pathetic
    0.89
    Activations Density 0.014%

    No Known Activations