© 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. 10-GEMMASCOPE-RES-131K
    4. 1298
    Prev
    Next
    INDEX
    Explanations

    flexible circuit boards

    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_10/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
     ésta
    -2.84
     you
    -2.44
     This
    -2.27
    にの
    -2.17
    --
    -2.16
     dicha
    -2.16
     обслуживание
    -2.06
     éste
    -2.05
     dichas
    -2.05
    </strong>
    -2.03
    POSITIVE LOGITS
     juga
    2.45
    "—
    2.08
    ‪.‬‬
    1.99
     gustaMe
    1.97
    ଽ
    1.92
     graden
    1.91
     dags
    1.90
    !");
    1.89
    ﺐ
    1.89
    т
    1.88
    Activations Density 0.001%

    No Known Activations