© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2565
    Prev
    Next
    INDEX
    Explanations

    quantization of model weights

    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_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
    ковник
    0.45
    setIcon
    0.44
     противополо
    0.44
    lavery
    0.43
    テナンス
    0.43
     />);
    0.43
    盱
    0.42
    剜
    0.42
    隽
    0.41
    लेंट
    0.41
    POSITIVE LOGITS
     quantization
    1.11
     quantized
    1.05
     inference
    0.96
     tensors
    0.87
    Tensor
    0.84
    inference
    0.80
     Tensor
    0.80
     Inference
    0.78
     torch
    0.78
     tensor
    0.78
    Activations Density 0.138%

    No Known Activations