© 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. 22-GEMMASCOPE-RES-131K
    7. 68034
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
     with
    -1.62
     in
    -1.60
     by
    -1.42
    </h3>
    -1.27
     Before
    -1.24
    Surprisingly
    -1.23
     When
    -1.23
     on
    -1.23
     بسیار
    -1.23
    </em>
    -1.21
    POSITIVE LOGITS
    莛
    1.30
     maniere
    1.29
     incendie
    1.27
    zied
    1.27
     huo
    1.27
    abinieri
    1.25
     diferentes
    1.22
     puedo
    1.22
    ocarditis
    1.20
    😊
    1.19
    Activations Density 0.034%

    No Known Activations