© 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. 173313
    Prev
    Next
    INDEX
    Explanations

    past states and conditions

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

    parts of speech and common words

    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
     escritos
    0.52
     mensagens
    0.48
     rápidamente
    0.45
    ួយ
    0.43
    წ
    0.43
    عت
    0.43
    도를
    0.43
    த
    0.42
     Fiona
    0.42
     szybko
    0.42
    POSITIVE LOGITS
    IO
    0.52
     nonnegative
    0.51
     ज़र
    0.50
    ہنی
    0.50
    REAM
    0.49
    ILABLE
    0.49
     приложения
    0.48
    NEE
    0.48
    AI
    0.48
     hydros
    0.48
    Activations Density 0.000%

    No Known Activations