© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34330
    Prev
    Next
    INDEX
    Explanations

    name="

    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
     produs
    -1.13
    訁
    -1.06
     disponib
    -1.03
     assistente
    -1.02
     applau
    -1.02
    )";
    -1.00
     discuter
    -0.99
    vindo
    -0.98
    тории
    -0.97
     publice
    -0.97
    POSITIVE LOGITS
     after
    1.29
     on
    1.22
     Without
    1.20
     tiada
    1.11
     répondit
    1.09
     Before
    1.09
     Through
    1.05
    masının
    1.05
    Before
    1.02
    After
    1.02
    Activations Density 0.019%

    No Known Activations