© 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. 53-GEMMASCOPE-2-RES-262K
    7. 37717
    Prev
    Next
    INDEX
    Explanations

    time periods and transitions

    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_53_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
    Late
    0.59
    late
    0.57
     late
    0.56
     Late
    0.53
     akhir
    0.49
     позд
    0.49
    晚
    0.48
    ④
    0.48
     kés
    0.43
     ④
    0.43
    POSITIVE LOGITS
     начале
    0.68
     into
    0.61
     beginning
    0.59
     начало
    0.57
     spilling
    0.54
     spill
    0.53
    Throughout
    0.53
     spilled
    0.53
    にかけて
    0.52
     transition
    0.52
    Activations Density 0.026%

    No Known Activations