© 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. 144409
    Prev
    Next
    INDEX
    Explanations

    related to fine-tuning dataset

    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
    "
    0.51
    5
    0.49
    ↵↵
    0.46
    এ
    0.44
    9
    0.43
    1
    0.41
    は
    0.40
    Q
    0.40
    とは思
    0.39
     চলা
    0.39
    POSITIVE LOGITS
     ಮಾಡಲು
    0.52
    >]</
    0.51
     സാധ
    0.49
    ्तिक
    0.48
    比如說
    0.48
     ইন্দু
    0.46
     imassa
    0.46
     വസ്തു
    0.45
     രണ്ട്
    0.45
     акы
    0.45
    Activations Density 0.002%

    No Known Activations