© 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. 14402
    Prev
    Next
    INDEX
    Explanations

    website links and dates

    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
    ♪♪
    -1.09
     Travail
    -1.05
    Стро
    -1.03
     LIRE
    -1.03
    Бан
    -1.01
     مقاله
    -1.01
    Égypte
    -0.99
    jazdu
    -0.98
    freundlich
    -0.98
    riebene
    -0.97
    POSITIVE LOGITS
    是怎么回事
    1.23
     about
    1.05
     along
    0.97
     ts
    0.91
    about
    0.88
    
    0.85
    ah
    0.84
    their
    0.84
     http
    0.82
     such
    0.81
    Activations Density 0.035%

    No Known Activations