© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2060
    Prev
    Next
    INDEX
    Explanations

    quantization bit levels (4-bit, 8-bit)

    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_40_width_65k_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
    besar
    0.44
    Latency
    0.42
    大きな
    0.42
    ப்பையும்
    0.41
    ремя
    0.41
    BufOffset
    0.40
     मल्टीप्लाई
    0.39
    :'],
    0.39
     ಬ್ಯಾ
    0.39
    elenggarakan
    0.38
    POSITIVE LOGITS
     quantization
    1.02
     Quant
    0.91
     quant
    0.91
     quantized
    0.85
    quant
    0.77
    Quant
    0.74
     quantification
    0.65
     Q
    0.61
     quan
    0.61
     Quan
    0.60
    Activations Density 0.104%

    No Known Activations