© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177392
    Prev
    Next
    INDEX
    Explanations

    Marketing Translation

    np_acts-logits-general · gemini-2.5-flash-lite

    actions, density, air, attempt, children, Brain, devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    棻
    0.52
     માટે
    0.48
     पाना
    0.45
     ב
    0.44
    šten
    0.44
    长期
    0.44
    Categoria
    0.43
    டா
    0.43
    м
    0.42
    ־
    0.42
    POSITIVE LOGITS
     meines
    0.46
     useNavigate
    0.44
     mêmes
    0.43
     ataupun
    0.43
    bayes
    0.42
    putText
    0.41
     Odysseus
    0.41
     supplémentaires
    0.41
    ীবনী
    0.40
    ৃহে
    0.40
    Activations Density 0.001%

    No Known Activations