© 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. 22-GEMMASCOPE-RES-131K
    4. 9483
    Prev
    Next
    INDEX
    Explanations

    text right now

    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
    {
    -1.19
    ),
    -1.13
     one
    -1.12
     ponieważ
    -1.09
     體
    -1.04
    ],
    -0.98
    箩
    -0.96
     vermutlich
    -0.95
     Surprisingly
    -0.95
     There
    -0.95
    POSITIVE LOGITS
    ఝ
    1.20
     libera
    1.15
     are
    1.10
     eten
    1.05
     biblia
    1.04
     indag
    1.02
    抬起
    1.02
     amazing
    1.00
     کر
    0.99
     talleres
    0.99
    Activations Density 0.056%

    No Known Activations