© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40609
    Prev
    Next
    INDEX
    Explanations

    Outer Wilds, following events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ând
    0.50
     تلك
    0.44
    خ
    0.43
    㮔
    0.43
    DEA
    0.42
     ellos
    0.42
    ':
    0.42
     aquela
    0.42
     hombre
    0.42
     man
    0.41
    POSITIVE LOGITS
     নেমে
    0.46
     চেষ্ট
    0.46
    存在する
    0.45
    всем
    0.45
    yfikacji
    0.42
    еве
    0.42
     legality
    0.41
     enacted
    0.41
    িনিয়ার
    0.41
     독
    0.41
    Activations Density 0.003%

    No Known Activations