© 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. 125957
    Prev
    Next
    INDEX
    Explanations

    tomorrow, it, *

    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
    Ე
    0.48
     उठता
    0.46
    ụ
    0.45
    ექ
    0.44
    делить
    0.44
    ُر
    0.44
     çarp
    0.44
    इन
    0.43
    कर्मी
    0.43
    唓
    0.43
    POSITIVE LOGITS
     اچھا
    0.50
     for
    0.48
     accurately
    0.48
     at
    0.46
     if
    0.46
     without
    0.45
     so
    0.43
     by
    0.43
     ethylene
    0.43
     them
    0.42
    Activations Density 0.001%

    No Known Activations